Topic Keywords

[ $\ell_1$ norm ] [ $f-$divergence ] [ 3D Convolution ] [ 3D deep learning ] [ 3D generation ] [ 3d point cloud ] [ 3D Reconstruction ] [ 3D scene understanding ] [ 3D shape representations ] [ 3D shapes learning ] [ 3D vision ] [ 3D Vision ] [ abstract reasoning ] [ abstract rules ] [ Acceleration ] [ accuracy ] [ acoustic condition modeling ] [ Action localization ] [ action recognition ] [ activation maximization ] [ activation strategy. ] [ Active learning ] [ Active Learning ] [ AdaBoost ] [ adaptive heavy-ball methods ] [ Adaptive Learning ] [ adaptive methods ] [ adaptive optimization ] [ ADMM ] [ Adversarial Accuracy ] [ Adversarial Attack ] [ Adversarial Attacks ] [ adversarial attacks/defenses ] [ Adversarial computer programs ] [ Adversarial Defense ] [ Adversarial Example Detection ] [ Adversarial Examples ] [ Adversarial Learning ] [ Adversarial Machine Learning ] [ adversarial patch ] [ Adversarial robustness ] [ Adversarial Robustness ] [ Adversarial training ] [ Adversarial Training ] [ Adversarial Transferability ] [ aesthetic assessment ] [ affine parameters ] [ age estimation ] [ Aggregation Methods ] [ AI for earth science ] [ ALFRED ] [ Algorithm ] [ algorithmic fairness ] [ Algorithmic fairness ] [ Algorithms ] [ alignment ] [ alignment of semantic and visual space ] [ amortized inference ] [ Analogies ] [ annotation artifacts ] [ anomaly-detection ] [ Anomaly detection with deep neural networks ] [ anonymous walk ] [ appearance transfer ] [ approximate constrained optimization ] [ approximation ] [ Approximation ] [ Architectures ] [ argoverse ] [ Artificial Integlligence ] [ ASR ] [ assistive technology ] [ associative memory ] [ Associative Memory ] [ asynchronous parallel algorithm ] [ Atari ] [ Attention ] [ Attention Mechanism ] [ Attention Modules ] [ attractors ] [ attributed walks ] [ Auction Theory ] [ audio understanding ] [ Audio-Visual ] [ audio visual learning ] [ audio-visual representation ] [ audio-visual representation learning ] [ Audio-visual sound separation ] [ audiovisual synthesis ] [ augmented deep reinforcement learning ] [ autodiff ] [ Autoencoders ] [ automated data augmentation ] [ automated machine learning ] [ automatic differentiation ] [ AutoML ] [ autonomous learning ] [ autoregressive language model ] [ Autoregressive Models ] [ AutoRL ] [ auxiliary information ] [ auxiliary latent variable ] [ Auxiliary Learning ] [ auxiliary task ] [ Average-case Analysis ] [ aversarial examples ] [ avoid knowledge leaking ] [ backdoor attack ] [ Backdoor Attacks ] [ Backdoor Defense ] [ Backgrounds ] [ backprop ] [ back translation ] [ backward error analysis ] [ bagging ] [ batchnorm ] [ Batch Normalization ] [ batch reinforcement learning ] [ Batch Reinforcement Learning ] [ batch selection ] [ Bayesian ] [ Bayesian classification ] [ Bayesian inference ] [ Bayesian Inference ] [ Bayesian networks ] [ Bayesian Neural Networks ] [ behavior cloning ] [ belief-propagation ] [ Benchmark ] [ benchmarks ] [ benign overfitting ] [ bert ] [ BERT ] [ beta-VAE ] [ better generalization ] [ biased sampling ] [ biases ] [ Bias in Language Models ] [ bidirectional ] [ bilevel optimization ] [ Bilinear games ] [ Binary Embeddings ] [ Binary Neural Networks ] [ binaural audio ] [ binaural speech ] [ biologically plausible ] [ Biometrics ] [ bisimulation ] [ Bisimulation ] [ bisimulation metrics ] [ bit-flip ] [ bit-level sparsity ] [ blind denoising ] [ blind spots ] [ block mdp ] [ boosting ] [ bottleneck ] [ bptt ] [ branch and bound ] [ Brownian motion ] [ Budget-Aware Pruning ] [ Budget constraints ] [ Byzantine resilience ] [ Byzantine SGD ] [ CAD modeling ] [ calibration ] [ Calibration ] [ calibration measure ] [ cancer research ] [ Capsule Networks ] [ Catastrophic forgetting ] [ Catastrophic Forgetting ] [ Causal Inference ] [ Causality ] [ Causal network ] [ certificate ] [ certified defense ] [ Certified Robustness ] [ challenge sets ] [ change of measure ] [ change point detection ] [ channel suppressing ] [ Channel Tensorization ] [ Channel-Wise Approximated Activation ] [ Chaos ] [ chebyshev polynomial ] [ checkpointing ] [ Checkpointing ] [ chemistry ] [ CIFAR ] [ Classification ] [ class imbalance ] [ clean-label ] [ Clustering ] [ Clusters ] [ CNN ] [ CNNs ] [ Code Compilation ] [ Code Representations ] [ Code Structure ] [ code summarization ] [ Code Summarization ] [ Cognitively-inspired Learning ] [ cold posteriors ] [ collaborative learning ] [ Combinatorial optimization ] [ common object counting ] [ commonsense question answering ] [ Commonsense Reasoning ] [ Communication Compression ] [ co-modulation ] [ complete verifiers ] [ complex query answering ] [ Composition ] [ compositional generalization ] [ compositional learning ] [ compositional task ] [ Compressed videos ] [ Compressing Deep Networks ] [ Compression ] [ computation ] [ computational biology ] [ Computational Biology ] [ computational complexity ] [ Computational imaging ] [ Computational neuroscience ] [ Computational resources ] [ computer graphics ] [ Computer Vision ] [ concentration ] [ Concentration of Measure ] [ Concept-based Explanation ] [ concept drift ] [ Concept Learning ] [ conditional expectation ] [ Conditional GANs ] [ Conditional Generation ] [ Conditional generative adversarial networks ] [ conditional layer normalization ] [ Conditional Neural Processes ] [ Conditional Risk Minimization ] [ Conditional Sampling ] [ conditional text generation ] [ Conferrability ] [ confidentiality ] [ conformal inference ] [ conformal prediction ] [ conjugacy ] [ conservation law ] [ consistency ] [ consistency training ] [ Consistency Training ] [ constellation models ] [ constrained beam search ] [ Constrained optimization ] [ constrained RL ] [ constraints ] [ constraint satisfaction ] [ contact tracing ] [ Contextual Bandits ] [ Contextual embedding space ] [ Continual learning ] [ Continual Learning ] [ continuation method ] [ continuous and scalar conditions ] [ continuous case ] [ Continuous Control ] [ continuous convolution ] [ continuous games ] [ continuous normalizing flow ] [ continuous time ] [ Continuous-time System ] [ continuous treatment effect ] [ contrastive divergence ] [ Contrastive learning ] [ Contrastive Learning ] [ Contrastive Methods ] [ contrastive representation learning ] [ control barrier function ] [ controlled generation ] [ Controlled NLG ] [ Convergence ] [ Convergence Analysis ] [ convex duality ] [ Convex optimization ] [ ConvNets ] [ convolutional kernel methods ] [ Convolutional Layer ] [ convolutional models ] [ Convolutional Networks ] [ copositive programming ] [ corruptions ] [ COST ] [ Counterfactual inference ] [ counterfactuals ] [ Counterfactuals ] [ covariant neural networks ] [ covid-19 ] [ COVID-19 ] [ Cross-domain ] [ cross-domain few-shot learning ] [ cross-domain video generation ] [ cross-episode attention ] [ cross-fitting ] [ cross-lingual pretraining ] [ Cryptographic inference ] [ cultural transmission ] [ Curriculum Learning ] [ curse of memory ] [ curvature estimates ] [ custom voice ] [ cycle-consistency regularization ] [ cycle-consistency regularizer ] [ DAG ] [ DARTS stability ] [ Data augmentation ] [ Data Augmentation ] [ data cleansing ] [ Data-driven modeling ] [ data-efficient learning ] [ data-efficient RL ] [ Data Flow ] [ data labeling ] [ data parallelism ] [ Data Poisoning ] [ Data Protection ] [ Dataset ] [ dataset bias ] [ dataset compression ] [ dataset condensation ] [ dataset corruption ] [ dataset distillation ] [ dataset summarization ] [ data structures ] [ debiased training ] [ debugging ] [ Decentralized Optimization ] [ decision boundary geometry ] [ decision trees ] [ declarative knowledge ] [ deep-anomaly-detection ] [ Deep Architectures ] [ Deep denoising priors ] [ deep embedding ] [ Deep Ensembles ] [ deep equilibrium models ] [ Deep Equilibrium Models ] [ Deepfake ] [ deep FBSDEs ] [ Deep Gaussian Processes ] [ Deep generative model ] [ Deep generative modeling ] [ Deep generative models ] [ deeplearning ] [ Deep learning ] [ Deep Learning ] [ deep learning dynamics ] [ Deep Learning Theory ] [ deep network training ] [ deep neural network ] [ deep neural networks. ] [ Deep Neural Networks ] [ deep one-class classification ] [ deep Q-learning ] [ Deep reinforcement learning ] [ Deep Reinforcement Learning ] [ deep ReLU networks ] [ Deep residual neural networks ] [ deep RL ] [ deep sequence model ] [ deepset ] [ Deep Sets ] [ Deformation Modeling ] [ delay ] [ Delay differential equations ] [ denoising score matching ] [ Dense Retrieval ] [ Density estimation ] [ Density Estimation ] [ Density ratio estimation ] [ dependency based method ] [ deployment-efficiency ] [ depression ] [ depth separation ] [ descent ] [ description length ] [ determinantal point processes ] [ Device Placement ] [ dialogue state tracking ] [ differentiable optimization ] [ Differentiable physics ] [ Differentiable Physics ] [ Differentiable program generator ] [ differentiable programming ] [ Differentiable rendering ] [ Differentiable simulation ] [ differential dynamica programming ] [ differential equations ] [ Differential Geometry ] [ differentially private deep learning ] [ Differential Privacy ] [ diffusion probabilistic models ] [ diffusion process ] [ dimension ] [ Directed Acyclic Graphs ] [ Dirichlet form ] [ Discrete Optimization ] [ discretization error ] [ disentangled representation learning ] [ Disentangled representation learning ] [ Disentanglement ] [ distance ] [ Distillation ] [ distinct elements ] [ Distributed ] [ distributed deep learning ] [ distributed inference ] [ Distributed learning ] [ distributed machine learning ] [ Distributed ML ] [ Distributed Optimization ] [ distributional robust optimization ] [ distribution estimation ] [ distribution shift ] [ diverse strategies ] [ diverse video generation ] [ Diversity denoising ] [ Diversity Regularization ] [ DNN ] [ DNN compression ] [ document analysis ] [ document classification ] [ document retrieval ] [ domain adaptation theory ] [ Domain Adaption ] [ Domain Generalization ] [ domain randomization ] [ Domain Translation ] [ double descent ] [ Double Descent ] [ doubly robustness ] [ Doubly-weighted Laplace operator ] [ Dropout ] [ drug discovery ] [ Drug discovery ] [ dst ] [ Dual-mode ASR ] [ Dueling structure ] [ Dynamical Systems ] [ dynamic computation graphs ] [ dynamics ] [ dynamics prediction ] [ dynamic systems ] [ Early classification ] [ Early pruning ] [ early stopping ] [ EBM ] [ Edit ] [ EEG ] [ effective learning rate ] [ Efficiency ] [ Efficient Attention Mechanism ] [ efficient deep learning ] [ Efficient Deep Learning ] [ Efficient Deep Learning Inference ] [ Efficient ensembles ] [ efficient inference ] [ efficient inference methods ] [ Efficient Inference Methods ] [ EfficientNets ] [ efficient network ] [ Efficient Networks ] [ Efficient training ] [ Efficient Training ] [ efficient training and inference. ] [ egocentric ] [ eigendecomposition ] [ Eigenspectrum ] [ ELBO ] [ electroencephalography ] [ EM ] [ Embedding Models ] [ Embedding Size ] [ Embodied Agents ] [ embodied vision ] [ emergent behavior ] [ empirical analysis ] [ Empirical Game Theory ] [ empirical investigation ] [ Empirical Investigation ] [ empirical study ] [ empowerment ] [ Encoder layer fusion ] [ end-to-end entity linking ] [ End-to-End Object Detection ] [ Energy ] [ Energy-Based GANs ] [ energy based model ] [ energy-based model ] [ Energy-based model ] [ energy based models ] [ Energy-based Models ] [ Energy Based Models ] [ Energy-Based Models ] [ Energy Score ] [ ensemble ] [ Ensemble ] [ ensemble learning ] [ ensembles ] [ Ensembles ] [ entity disambiguation ] [ entity linking ] [ entity retrieval ] [ entropic algorithms ] [ Entropy Maximization ] [ Entropy Model ] [ entropy regularization ] [ epidemiology ] [ episode-level pretext task ] [ episodic training ] [ equilibrium ] [ equivariant ] [ equivariant neural network ] [ ERP ] [ Evaluation ] [ evaluation of interpretability ] [ Event localization ] [ evolution ] [ Evolutionary algorithm ] [ Evolutionary Algorithm ] [ Evolutionary Algorithms ] [ Excess risk ] [ experience replay buffer ] [ experimental evaluation ] [ Expert Models ] [ Explainability ] [ explainable ] [ Explainable AI ] [ Explainable Model ] [ explaining decision-making ] [ explanation method ] [ explanations ] [ Explanations ] [ Exploration ] [ Exponential Families ] [ exponential tilting ] [ exposition ] [ external memory ] [ Extrapolation ] [ extremal sector ] [ facial recognition ] [ factor analysis ] [ factored MDP ] [ Factored MDP ] [ fairness ] [ Fairness ] [ faithfulness ] [ fast DNN inference ] [ fast learning rate ] [ fast-mapping ] [ fast weights ] [ FAVOR ] [ Feature Attribution ] [ feature propagation ] [ features ] [ feature visualization ] [ Feature Visualization ] [ Federated learning ] [ Federated Learning ] [ Few Shot ] [ few-shot concept learning ] [ few-shot domain generalization ] [ Few-shot learning ] [ Few Shot Learning ] [ fine-tuning ] [ finetuning ] [ Fine-tuning ] [ Finetuning ] [ fine-tuning stability ] [ Fingerprinting ] [ First-order Methods ] [ first-order optimization ] [ fisher ratio ] [ flat minima ] [ Flexibility ] [ flow graphs ] [ Fluid Dynamics ] [ Follow-the-Regularized-Leader ] [ Formal Verification ] [ forward mode ] [ Fourier Features ] [ Fourier transform ] [ framework ] [ Frobenius norm ] [ from-scratch ] [ frontend ] [ fruit fly ] [ fully-connected ] [ Fully-Connected Networks ] [ future frame generation ] [ future link prediction ] [ fuzzy tiling activation function ] [ Game Decomposition ] [ Game Theory ] [ GAN ] [ GAN compression ] [ GANs ] [ Garbled Circuits ] [ Gaussian Copula ] [ Gaussian Graphical Model ] [ Gaussian Isoperimetric Inequality ] [ Gaussian mixture model ] [ Gaussian process ] [ Gaussian Process ] [ Gaussian Processes ] [ gaussian process priors ] [ GBDT ] [ generalisation ] [ Generalization ] [ Generalization Bounds ] [ generalization error ] [ Generalization Measure ] [ Generalization of Reinforcement Learning ] [ generalized ] [ generalized Girsanov theorem ] [ Generalized PageRank ] [ Generalized zero-shot learning ] [ Generation ] [ Generative Adversarial Network ] [ Generative Adversarial Networks ] [ generative art ] [ Generative Flow ] [ Generative Model ] [ Generative modeling ] [ Generative Modeling ] [ generative modelling ] [ Generative Modelling ] [ Generative models ] [ Generative Models ] [ genetic programming ] [ Geodesic-Aware FC Layer ] [ geometric ] [ Geometric Deep Learning ] [ G-invariance regularization ] [ global ] [ global optima ] [ Global Reference ] [ glue ] [ GNN ] [ GNNs ] [ goal-conditioned reinforcement learning ] [ goal-conditioned RL ] [ goal reaching ] [ gradient ] [ gradient alignment ] [ Gradient Alignment ] [ gradient boosted decision trees ] [ gradient boosting ] [ gradient decomposition ] [ Gradient Descent ] [ gradient descent-ascent ] [ gradient flow ] [ Gradient flow ] [ gradient flows ] [ gradient redundancy ] [ Gradient stability ] [ Grammatical error correction ] [ Granger causality ] [ Graph ] [ graph classification ] [ graph coarsening ] [ Graph Convolutional Network ] [ Graph Convolutional Neural Networks ] [ graph edit distance ] [ Graph Generation ] [ Graph Generative Model ] [ graph-level prediction ] [ graph networks ] [ Graph neural network ] [ Graph Neural Network ] [ Graph neural networks ] [ Graph Neural Networks ] [ Graph pooling ] [ graph representation learning ] [ Graph representation learning ] [ Graph Representation Learning ] [ graph shift operators ] [ graph-structured data ] [ graph structure learning ] [ Greedy Learning ] [ grid cells ] [ grounding ] [ group disparities ] [ group equivariance ] [ Group Equivariance ] [ Group Equivariant Convolution ] [ group equivariant self-attention ] [ group equivariant transformers ] [ group sparsity ] [ Group-supervised learning ] [ gumbel-softmax ] [ Hamiltonian systems ] [ hard-label attack ] [ hard negative mining ] [ hard negative sampling ] [ Hardware-Aware Neural Architecture Search ] [ Harmonic Analysis ] [ harmonic distortion analysis ] [ healthcare ] [ Healthcare ] [ heap allocation ] [ Hessian matrix ] [ Heterogeneity ] [ Heterogeneous ] [ heterogeneous data ] [ Heterogeneous data ] [ Heterophily ] [ heteroscedasticity ] [ heuristic search ] [ hidden-parameter mdp ] [ hierarchical contrastive learning ] [ Hierarchical Imitation Learning ] [ Hierarchical Multi-Agent Learning ] [ Hierarchical Networks ] [ Hierarchical Reinforcement Learning ] [ Hierarchy-Aware Classification ] [ high-dimensional asymptotics ] [ high-dimensional statistic ] [ high-resolution video generation ] [ hindsight relabeling ] [ histogram binning ] [ historical color image classification ] [ HMC ] [ homomorphic encryption ] [ Homophily ] [ Hopfield layer ] [ Hopfield networks ] [ Hopfield Networks ] [ human-AI collaboration ] [ human cognition ] [ human-computer interaction ] [ human preferences ] [ human psychophysics ] [ humans in the loop ] [ hybrid systems ] [ Hyperbolic ] [ hyperbolic deep learning ] [ Hyperbolic Geometry ] [ hypercomplex representation learning ] [ hypergradients ] [ Hypernetworks ] [ hyperparameter ] [ Hyperparameter Optimization ] [ Hyper-Parameter Optimization ] [ HYPERPARAMETER OPTIMIZATION ] [ Image Classification ] [ image completion ] [ Image compression ] [ Image Editing ] [ Image Generation ] [ Image manipulation ] [ Image Modeling ] [ ImageNet ] [ image reconstruction ] [ Image segmentation ] [ Image Synthesis ] [ image-to-action learning ] [ Image-to-Image Translation ] [ image translation ] [ image warping ] [ imbalanced learning ] [ Imitation Learning ] [ Impartial Learning ] [ implicit bias ] [ Implicit Bias ] [ Implicit Deep Learning ] [ implicit differentiation ] [ implicit functions ] [ implicit neural representations ] [ Implicit Neural Representations ] [ Implicit Representation ] [ Importance Weighting ] [ impossibility ] [ incoherence ] [ Incompatible Environments ] [ Incremental Tree Transformations ] [ independent component analysis ] [ indirection ] [ Individual mediation effects ] [ Inductive Bias ] [ inductive biases ] [ inductive representation learning ] [ infinitely wide neural network ] [ Infinite-Width Limit ] [ infinite-width networks ] [ influence functions ] [ Influence Functions ] [ Information bottleneck ] [ Information Bottleneck ] [ Information Geometry ] [ information-theoretical probing ] [ Information theory ] [ Information Theory ] [ Initialization ] [ input-adaptive multi-exit neural networks ] [ input convex neural networks ] [ input-convex neural networks ] [ InstaHide ] [ Instance adaptation ] [ instance-based label noise ] [ Instance learning ] [ Instance-wise Learning ] [ Instrumental Variable Regression ] [ integral probability metric ] [ intention ] [ interaction networks ] [ Interactions ] [ interactive fiction ] [ Internet of Things ] [ Interpolation Peak ] [ Interpretability ] [ interpretable latent representation ] [ Interpretable Machine Learning ] [ interpretable policy learning ] [ in-the-wild data ] [ Intrinsically Motivated Reinforcement Learning ] [ Intrinsic Motivation ] [ intrinsic motivations ] [ Intrinsic Reward ] [ Invariance and Equivariance ] [ invariance penalty ] [ invariances ] [ Invariant and equivariant deep networks ] [ Invariant Representations ] [ invariant risk minimization ] [ Invariant subspaces ] [ inverse graphics ] [ Inverse reinforcement learning ] [ Inverse Reinforcement Learning ] [ Inverted Index ] [ irl ] [ IRM ] [ irregularly spaced time series ] [ irregular-observed data modelling ] [ isometric ] [ Isotropy ] [ iterated learning ] [ iterative training ] [ JEM ] [ Johnson-Lindenstrauss Transforms ] [ kernel ] [ Kernel Learning ] [ kernel method ] [ kernel-ridge regression ] [ kernels ] [ keypoint localization ] [ Knowledge distillation ] [ Knowledge Distillation ] [ Knowledge factorization ] [ Knowledge Graph Reasoning ] [ knowledge uncertainty ] [ Kullback-Leibler divergence ] [ Kurdyka-Łojasiewicz geometry ] [ label noise robustness ] [ Label Representation ] [ Label shift ] [ label smoothing ] [ Langevin dynamics ] [ Langevin sampling ] [ Language Grounding ] [ Language Model ] [ Language modeling ] [ Language Modeling ] [ Language Modelling ] [ Language Model Pre-training ] [ language processing ] [ language-specific modeling ] [ Laplace kernel ] [ Large-scale ] [ Large-scale Deep Learning ] [ large scale learning ] [ Large-scale Machine Learning ] [ large-scale pre-trained language models ] [ large-scale training ] [ large vocabularies ] [ Last-iterate Convergence ] [ Latency-aware Neural Architecture Search ] [ Latent Simplex ] [ latent space of GANs ] [ Latent Variable Models ] [ lattices ] [ Layer order ] [ layerwise sparsity ] [ learnable ] [ learned algorithms ] [ Learned compression ] [ learned ISTA ] [ Learning ] [ learning action representations ] [ learning-based ] [ learning dynamics ] [ Learning Dynamics ] [ Learning in Games ] [ learning mechanisms ] [ Learning physical laws ] [ Learning Theory ] [ Learning to Hash ] [ learning to optimize ] [ Learning to Optimize ] [ learning to rank ] [ Learning to Rank ] [ learning to teach ] [ learning with noisy labels ] [ Learning with noisy labels ] [ library ] [ lifelong ] [ Lifelong learning ] [ Lifelong Learning ] [ lifted inference ] [ likelihood-based models ] [ likelihood-free inference ] [ limitations ] [ limited data ] [ linear bandits ] [ Linear Convergence ] [ linear estimator ] [ Linear Regression ] [ linear terms ] [ linformer ] [ Lipschitz constants ] [ Lipschitz constrained networks ] [ Local Explanations ] [ locality sensitive hashing ] [ Locally supervised training ] [ local Rademacher complexity ] [ log-concavity ] [ Logic ] [ Logic Rules ] [ logsignature ] [ Long-Tailed Recognition ] [ long-tail learning ] [ Long-term dependencies ] [ long-term prediction ] [ long-term stability ] [ loss correction ] [ Loss function search ] [ Loss Function Search ] [ lossless source compression ] [ Lottery Ticket ] [ Lottery Ticket Hypothesis ] [ lottery tickets ] [ low-dimensional structure ] [ lower bound ] [ lower bounds ] [ Low-latency ASR ] [ low precision training ] [ low rank ] [ low-rank approximation ] [ low-rank tensors ] [ L-smoothness ] [ LSTM ] [ Lyapunov Chaos ] [ Machine learning ] [ Machine Learning ] [ machine learning for code ] [ Machine Learning for Robotics ] [ Machine Learning (ML) for Programming Languages (PL)/Software Engineering (SE) ] [ machine learning systems ] [ Machine translation ] [ Machine Translation ] [ magnitude-based pruning ] [ Manifold clustering ] [ Manifolds ] [ Many-task ] [ mapping ] [ Markov chain Monte Carlo ] [ Markov Chain Monte Carlo ] [ Markov jump process ] [ Masked Reconstruction ] [ mathematical reasoning ] [ Matrix and Tensor Factorization ] [ matrix completion ] [ matrix decomposition ] [ Matrix Factorization ] [ max-margin ] [ MCMC ] [ MCMC sampling ] [ mean estimation ] [ mean-field dynamics ] [ mean separation ] [ Mechanism Design ] [ medical time series ] [ mel-filterbanks ] [ memorization ] [ Memorization ] [ Memory ] [ memory efficient ] [ memory efficient training ] [ Memory Mapping ] [ memory optimized training ] [ Memory-saving ] [ mesh ] [ Message Passing ] [ Message Passing GNNs ] [ meta-gradients ] [ Meta-learning ] [ Meta Learning ] [ Meta-Learning ] [ Metric Surrogate ] [ minimax optimal rate ] [ Minimax Optimization ] [ minimax risk ] [ Minmax ] [ min-max optimization ] [ mirror-prox ] [ Missing Data Inference ] [ Missing value imputation ] [ Missing Values ] [ misssing data ] [ mixed precision ] [ Mixed Precision ] [ Mixed-precision quantization ] [ mixture density nets ] [ mixture of experts ] [ mixup ] [ Mixup ] [ MixUp ] [ MLaaS ] [ MoCo ] [ Model Attribution ] [ model-based control ] [ model-based learning ] [ Model-based Reinforcement Learning ] [ Model-Based Reinforcement Learning ] [ model-based RL ] [ Model-based RL ] [ Model Biases ] [ Model compression ] [ model extraction ] [ model fairness ] [ Model Inversion ] [ model order reduction ] [ model ownership ] [ model predictive control ] [ model-predictive control ] [ Model Predictive Control ] [ Model privacy ] [ Models for code ] [ models of learning and generalization ] [ Model stealing ] [ Modern Hopfield Network ] [ modern Hopfield networks ] [ modified equation analysis ] [ modular architectures ] [ Modular network ] [ modular networks ] [ modular neural networks ] [ modular representations ] [ modulated convolution ] [ Molecular conformation generation ] [ molecular design ] [ Molecular Dynamics ] [ molecular graph generation ] [ Molecular Representation ] [ Molecule Design ] [ Momentum ] [ momentum methods ] [ momentum optimizer ] [ monotonicity ] [ Monte Carlo ] [ Monte-Carlo tree search ] [ Monte Carlo Tree Search ] [ morphology ] [ Morse theory ] [ mpc ] [ Multi-agent ] [ Multi-agent games ] [ Multiagent Learning ] [ multi-agent platform ] [ Multi-Agent Policy Gradients ] [ Multi-agent reinforcement learning ] [ Multi-agent Reinforcement Learning ] [ Multi-Agent Reinforcement Learning ] [ Multi-Agent Transfer Learning ] [ multiclass classification ] [ multi-dimensional discrete action spaces ] [ Multi-domain ] [ multi-domain disentanglement ] [ multi-head attention ] [ Multi-Hop ] [ multi-hop question answering ] [ Multi-hop Reasoning ] [ Multilingual Modeling ] [ multilingual representations ] [ multilingual transformer ] [ multilingual translation ] [ Multimodal ] [ Multi-Modal ] [ Multimodal Attention ] [ multi-modal learning ] [ Multimodal Learning ] [ Multi-Modal Learning ] [ Multimodal Spaces ] [ Multi-objective optimization ] [ multi-player ] [ Multiplicative Weights Update ] [ Multi-scale Representation ] [ multitask ] [ Multi-task ] [ Multi-task Learning ] [ Multi Task Learning ] [ Multi-Task Learning ] [ multi-task learning theory ] [ Multitask Reinforcement Learning ] [ Multi-view Learning ] [ Multi-View Learning ] [ Multi-view Representation Learning ] [ Mutual Information ] [ MuZero ] [ Named Entity Recognition ] [ NAS ] [ nash ] [ natural gradient descent ] [ Natural Language Processing ] [ natural scene statistics ] [ natural sparsity ] [ Negative Sampling ] [ negotiation ] [ nested optimization ] [ network architecture ] [ Network Architecture ] [ Network Inductive Bias ] [ network motif ] [ Network pruning ] [ Network Pruning ] [ networks ] [ network trainability ] [ network width ] [ Neural Architecture Search ] [ Neural Attention Distillation ] [ neural collapse ] [ Neural data compression ] [ Neural IR ] [ neural kernels ] [ neural link prediction ] [ Neural Model Explanation ] [ neural module network ] [ Neural Network ] [ Neural Network Bounding ] [ neural network calibration ] [ Neural Network Gaussian Process ] [ neural network robustness ] [ Neural networks ] [ Neural Networks ] [ neural network training ] [ Neural Network Verification ] [ neural ode ] [ Neural ODE ] [ Neural ODEs ] [ Neural operators ] [ Neural Physics Engines ] [ Neural Processes ] [ neural reconstruction ] [ neural sound synthesis ] [ neural spike train ] [ neural symbolic reasoning ] [ neural tangent kernel ] [ Neural tangent kernel ] [ Neural Tangent Kernel ] [ neural tangent kernels ] [ Neural text decoding ] [ neurobiology ] [ Neuroevolution ] [ Neuro symbolic ] [ Neuro-Symbolic Learning ] [ neuro-symbolic models ] [ NLI ] [ NLP ] [ Node Embeddings ] [ noise contrastive estimation ] [ Noise-contrastive learning ] [ Noise model ] [ noise robust learning ] [ Noisy Demonstrations ] [ noisy label ] [ Noisy Label ] [ Noisy Labels ] [ Non-asymptotic Confidence Intervals ] [ non-autoregressive generation ] [ nonconvex ] [ non-convex learning ] [ Non-Convex Optimization ] [ Non-IID ] [ nonlinear control theory ] [ nonlinear dynamical systems ] [ nonlinear Hawkes process ] [ nonlinear walk ] [ Non-Local Modules ] [ non-minimax optimization ] [ nonnegative PCA ] [ nonseparable Hailtonian system ] [ non-smooth models ] [ non-stationary stochastic processes ] [ no-regret learning ] [ normalized maximum likelihood ] [ normalize layer ] [ normalizers ] [ Normalizing Flow ] [ normalizing flows ] [ Normalizing flows ] [ Normalizing Flows ] [ normative models ] [ novelty-detection ] [ ntk ] [ number of linear regions ] [ numerical errors ] [ numerical linear algebra ] [ object-centric representations ] [ Object detection ] [ Object Detection ] [ object-keypoint representations ] [ ObjectNet ] [ Object Permanence ] [ Observational Imitation ] [ ODE ] [ offline ] [ offline/batch reinforcement learning ] [ off-line reinforcement learning ] [ offline reinforcement learning ] [ Offline Reinforcement Learning ] [ offline RL ] [ off-policy evaluation ] [ Off Policy Evaluation ] [ Off-policy policy evaluation ] [ Off-Policy Reinforcement Learning ] [ off-policy RL ] [ one-class-classification ] [ one-to-many mapping ] [ Open-domain ] [ open domain complex question answering ] [ open source ] [ Optimal Control Theory ] [ optimal convergence ] [ optimal power flow ] [ Optimal Transport ] [ optimal transport maps ] [ Optimisation for Deep Learning ] [ optimism ] [ Optimistic Gradient Descent Ascent ] [ Optimistic Mirror Decent ] [ Optimistic Multiplicative Weights Update ] [ Optimization ] [ order learning ] [ ordinary differential equation ] [ orthogonal ] [ orthogonal layers ] [ orthogonal machine learning ] [ Orthogonal Polynomials ] [ Oscillators ] [ outlier detection ] [ outlier-detection ] [ Outlier detection ] [ out-of-distribution ] [ Out-of-distribution detection in deep learning ] [ out-of-distribution generalization ] [ Out-of-domain ] [ over-fitting ] [ Overfitting ] [ overparameterisation ] [ over-parameterization ] [ Over-parameterization ] [ Overparameterization ] [ overparameterized neural networks ] [ Over-smoothing ] [ Oversmoothing ] [ over-squashing ] [ PAC Bayes ] [ padding ] [ parallel Monte Carlo Tree Search (MCTS) ] [ parallel tempering ] [ Parameter-Reduced MLR ] [ part-based ] [ Partial Amortization ] [ Partial differential equation ] [ partial differential equations ] [ partially observed environments ] [ particle inference ] [ pca ] [ pde ] [ pdes ] [ PDEs ] [ performer ] [ persistence diagrams ] [ personalized learning ] [ perturbation sets ] [ Peter-Weyl Theorem ] [ phase retrieval ] [ Physical parameter estimation ] [ physical reasoning ] [ physical scene understanding ] [ Physical Simulation ] [ physical symbol grounding ] [ physics ] [ physics-guided deep learning ] [ piecewise linear function ] [ pipeline toolkit ] [ plan-based reward shaping ] [ Planning ] [ Poincaré Ball Model ] [ Point cloud ] [ Point clouds ] [ point processes ] [ pointwise mutual information ] [ poisoning ] [ poisoning attack ] [ poisson matrix factorization ] [ policy learning ] [ Policy Optimization ] [ polynomial time ] [ Pose Estimation ] [ Position Embedding ] [ Position Encoding ] [ post-hoc calibration ] [ Post-Hoc Correction ] [ Post Training Quantization ] [ power grid management ] [ Predictive Modeling ] [ predictive uncertainty ] [ Predictive Uncertainty Estimation ] [ pretrained language model ] [ pretrained language model. ] [ pre-trained language model fine-tuning ] [ Pretrained Language Models ] [ Pretrained Text Encoders ] [ pre-training ] [ Pre-training ] [ Primitive Discovery ] [ principal components analysis ] [ Privacy ] [ privacy leakage from gradients ] [ privacy preserving machine learning ] [ Privacy-utility tradeoff ] [ probabelistic models ] [ probabilistic generative models ] [ probabilistic inference ] [ probabilistic matrix factorization ] [ Probabilistic Methods ] [ probabilistic multivariate forecasting ] [ probabilistic numerics ] [ probabilistic programs ] [ probably approximated correct guarantee ] [ Probe ] [ probing ] [ procedural generation ] [ procedural knowledge ] [ product of experts ] [ Product Quantization ] [ Program obfuscation ] [ Program Synthesis ] [ Proper Scoring Rules ] [ protein ] [ prototype propagation ] [ Provable Robustness ] [ provable sample efficiency ] [ proximal gradient descent-ascent ] [ proxy ] [ Pruning ] [ Pruning at initialization ] [ pseudo-labeling ] [ Pseudo-Labeling ] [ QA ] [ Q-learning ] [ Quantization ] [ quantum machine learning ] [ quantum mechanics ] [ Quantum Mechanics ] [ Question Answering ] [ random ] [ Random Feature ] [ Random Features ] [ Randomized Algorithms ] [ Random Matrix Theory ] [ Random Weights Neural Networks ] [ rank-collapse ] [ rank-constrained convex optimization ] [ rao ] [ rao-blackwell ] [ Rate-distortion optimization ] [ raven's progressive matrices ] [ real time recurrent learning ] [ real-world ] [ Real-world image denoising ] [ reasoning paths ] [ recommendation systems ] [ recommender system ] [ Recommender Systems ] [ recovery likelihood ] [ rectified linear unit ] [ Recurrent Generative Model ] [ Recurrent Neural Network ] [ Recurrent neural networks ] [ Recurrent Neural Networks ] [ recursive dense retrieval ] [ reformer ] [ regime agnostic methods ] [ Regression ] [ Regression without correspondence ] [ regret analysis ] [ regret minimization ] [ Regularization ] [ Regularization by denoising ] [ regularized markov decision processes ] [ Reinforcement ] [ Reinforcement learning ] [ Reinforcement Learning ] [ Reinforcement Learnings ] [ Reinforcement learning theory ] [ relabelling ] [ Relational regularized autoencoder ] [ Relation Extraction ] [ relaxed regularization ] [ relu network ] [ ReLU networks ] [ Rematerialization ] [ Render-and-Compare ] [ Reparameterization ] [ repetitions ] [ replica exchange ] [ representational learning ] [ representation analysis ] [ Representation learning ] [ Representation Learning ] [ representation learning for computer vision ] [ representation learning for robotics ] [ representation of dynamical systems ] [ Representation Theory ] [ reproducibility ] [ reproducible research ] [ Reproducing kernel Hilbert space ] [ resampling ] [ reset-free ] [ residual ] [ ResNets ] [ resource constrained ] [ Restricted Boltzmann Machines ] [ retraining ] [ Retrieval ] [ reverse accuracy ] [ reverse engineering ] [ reward learning ] [ reward randomization ] [ reward shaping ] [ reweighting ] [ Rich observation ] [ rich observations ] [ risk-averse ] [ Risk bound ] [ Risk Estimation ] [ risk sensitive ] [ rl ] [ RMSprop ] [ RNA-protein interaction prediction ] [ RNA structure ] [ RNA structure embedding ] [ RNN ] [ RNNs ] [ robotic manipulation ] [ robust ] [ robust control ] [ robust deep learning ] [ Robust Deep Learning ] [ robust learning ] [ Robust Learning ] [ Robust Machine Learning ] [ Robustness ] [ Robustness certificates ] [ Robust Overfitting ] [ ROC ] [ Role-Based Learning ] [ rooted graphs ] [ Rotation invariance ] [ rtrl ] [ Runtime Systems ] [ Saddle-point Optimization ] [ safe ] [ Safe exploration ] [ safe planning ] [ Saliency ] [ Saliency Guided Data Augmentation ] [ saliency maps ] [ SaliencyMix ] [ sample complexity separation ] [ Sample Efficiency ] [ sample information ] [ sample reweighting ] [ Sampling ] [ sampling algorithms ] [ Scalability ] [ Scale ] [ scale-invariant weights ] [ Scale of initialization ] [ scene decomposition ] [ scene generation ] [ Scene Understanding ] [ Science ] [ science of deep learning ] [ score-based generative models ] [ score matching ] [ score-matching ] [ SDE ] [ Second-order analysis ] [ second-order approximation ] [ second-order optimization ] [ Security ] [ segmented models ] [ selective classification ] [ Self-Imitation ] [ self supervised learning ] [ Self-supervised learning ] [ Self-supervised Learning ] [ Self Supervised Learning ] [ Self-Supervised Learning ] [ self-supervision ] [ self-training ] [ self-training theory ] [ semantic anomaly detection ] [ semantic directions in latent space ] [ semantic graphs ] [ Semantic Image Synthesis ] [ semantic parsing ] [ semantic role labeling ] [ semantic-segmentation ] [ Semantic Segmentation ] [ Semantic Textual Similarity ] [ semi-infinite duality ] [ semi-nonnegative matrix factorization ] [ semiparametric inference ] [ semi-supervised ] [ Semi-supervised Learning ] [ Semi-Supervised Learning ] [ semi-supervised learning theory ] [ Sentence Embeddings ] [ Sentence Representations ] [ Sentiment ] [ separation of variables ] [ Sequence Data ] [ Sequence Modeling ] [ sequence models ] [ Sequence-to-sequence learning ] [ sequence-to-sequence models ] [ sequential data ] [ Sequential probability ratio test ] [ Sequential Representation Learning ] [ set prediction ] [ set transformer ] [ SGD ] [ SGD noise ] [ sgld ] [ Shape ] [ shape bias ] [ Shape Bias ] [ Shape Encoding ] [ shapes ] [ Shapley values ] [ Sharpness Minimization ] [ side channel analysis ] [ Sigma Delta Quantization ] [ sign agnostic learning ] [ signal propagation ] [ signature ] [ sim2real ] [ sim2real transfer ] [ simple ] [ Singularity analysis ] [ singular value decomposition ] [ Sinkhorn algorithm ] [ skeleton-based action recognition ] [ sketch-based modeling ] [ sketches ] [ Skill Discovery ] [ SLAM ] [ sliced fused Gromov Wasserstein ] [ Sliced Wasserstein ] [ Slowdown attacks ] [ slowness ] [ Smooth games ] [ smoothing ] [ SMT Solvers ] [ social perception ] [ Soft Body ] [ soft labels ] [ software ] [ sound classification ] [ sound spatialization ] [ Source Code ] [ sparse Bayesian learning ] [ Sparse Embedding ] [ sparse embeddings ] [ sparse reconstruction ] [ sparse representation ] [ sparse representations ] [ sparse stochastic gates ] [ Sparsity ] [ Sparsity Learning ] [ spatial awareness ] [ spatial bias ] [ spatial uncertainty ] [ spatio-temporal forecasting ] [ spatio-temporal graph ] [ spatio-temporal modeling ] [ spatio-temporal modelling ] [ spatiotemporal prediction ] [ Spatiotemporal Understanding ] [ Spectral Analysis ] [ Spectral Distribution ] [ Spectral Graph Filter ] [ spectral regularization ] [ speech generation ] [ speech-impaired ] [ speech processing ] [ speech recognition. ] [ Speech Recognition ] [ spherical distributions ] [ spiking neural network ] [ spurious correlations ] [ square loss vs cross-entropy ] [ stability theory ] [ State abstraction ] [ state abstractions ] [ state-space models ] [ statistical learning theory ] [ Statistical Learning Theory ] [ statistical physics ] [ Statistical Physics ] [ statistical physics methods ] [ Steerable Kernel ] [ Stepsize optimization ] [ stochastic asymptotics ] [ stochastic control ] [ (stochastic) gradient descent ] [ Stochastic Gradient Descent ] [ stochastic gradient Langevin dynamics ] [ stochastic process ] [ Stochastic Processes ] [ stochastic subgradient method ] [ Storage Capacity ] [ straight-through ] [ straightthrough ] [ strategic behavior ] [ Streaming ASR ] [ structural biology ] [ structural credit assignment ] [ structural inductive bias ] [ Structured Pruning ] [ Structure learning ] [ structure prediction ] [ structures prediction ] [ Style Mixing ] [ Style Transfer ] [ subgraph reasoning. ] [ sublinear ] [ submodular optimization ] [ Subspace clustering ] [ Summarization ] [ summary statistics ] [ superpixel ] [ supervised contrastive learning ] [ Supervised Deep Networks ] [ Supervised Learning ] [ support estimation ] [ surprisal ] [ surrogate models ] [ svd ] [ SVD ] [ Symbolic Methods ] [ symbolic regression ] [ symbolic representations ] [ Symmetry ] [ symplectic networks ] [ Syntax ] [ Synthetic benchmark dataset ] [ synthetic-to-real generalization ] [ Systematic generalisation ] [ Systematicity ] [ System identification ] [ Tabular ] [ tabular data ] [ Tabular Data ] [ targeted attack ] [ Task Embeddings ] [ task generation ] [ task-oriented dialogue ] [ Task-oriented Dialogue System ] [ task reduction ] [ Task Segmentation ] [ Teacher-Student Learning ] [ teacher-student model ] [ temporal context ] [ Temporal knowledge graph ] [ temporal networks ] [ tensor product ] [ Text-based Games ] [ Text Representation ] [ Text Retrieval ] [ Text to speech ] [ Text to speech synthesis ] [ text-to-sql ] [ Texture ] [ Texture Bias ] [ Textworld ] [ Theorem proving ] [ theoretical issues in deep learning ] [ theoretical limits ] [ theoretical study ] [ Theory ] [ Theory of deep learning ] [ theory of mind ] [ Third-Person Imitation ] [ Thompson sampling ] [ time-frequency representations ] [ timescale ] [ timescales ] [ Time Series ] [ Time series forecasting ] [ time series prediction ] [ topic modelling ] [ Topology ] [ training dynamics ] [ Training Method ] [ trajectory ] [ trajectory optimization ] [ trajectory prediction ] [ Transferability ] [ Transfer learning ] [ Transfer Learning ] [ transformation invariance ] [ Transformer ] [ Transformers ] [ traveling salesperson problem ] [ Tree-structured Data ] [ trembl ] [ tropical function ] [ trust region ] [ two-layer neural network ] [ Uncertainty ] [ uncertainty calibration ] [ Uncertainty estimates ] [ Uncertainty estimation ] [ Uncertainty Machine Learning ] [ understanding ] [ understanding CNNs ] [ Understanding Data Augmentation ] [ understanding decision-making ] [ understanding deep learning ] [ Understanding Deep Learning ] [ understanding neural networks ] [ U-Net ] [ unidirectional ] [ uniprot ] [ universal approximation ] [ Universal approximation ] [ Universality ] [ universal representation learning ] [ universal sound separation ] [ unlabeled data ] [ Unlabeled Entity Problem ] [ Unlearnable Examples ] [ unrolled algorithms ] [ Unsupervised denoising ] [ Unsupervised Domain Translation ] [ unsupervised image denoising ] [ Unsupervised learning ] [ Unsupervised Learning ] [ unsupervised learning theory ] [ unsupervised loss ] [ Unsupervised Meta-learning ] [ unsupervised object discovery ] [ Unsupervised reinforcement learning ] [ unsupervised skill discovery ] [ unsupervised stabilization ] [ Upper Confidence bound applied to Trees (UCT) ] [ Usable Information ] [ VAE ] [ Value factorization ] [ value learning ] [ vanishing gradient problem ] [ variable binding ] [ variable convergence ] [ Variable Embeddings ] [ Variance Networks ] [ Variational Auto-encoder ] [ Variational autoencoders ] [ Variational Autoencoders ] [ Variational inference ] [ variational information bottleneck ] [ Verification ] [ video analysis ] [ Video Classification ] [ Video Compression ] [ video generation ] [ video-grounded dialogues ] [ Video prediction ] [ Video Reasoning ] [ video recognition ] [ Video Recognition ] [ video representation learning ] [ video synthesis ] [ video-text learning ] [ views ] [ virtual environment ] [ vision-and-language-navigation ] [ visual counting ] [ visualization ] [ visual perception ] [ Visual Reasoning ] [ visual reinforcement learning ] [ visual representation learning ] [ visual saliency ] [ vocoder ] [ voice conversion ] [ Volume Analysis ] [ VQA ] [ vulnerability of RL ] [ wanet ] [ warping functions ] [ Wasserstein ] [ wasserstein-2 barycenters ] [ wasserstein-2 distance ] [ Wasserstein distance ] [ waveform generation ] [ weakly-supervised learning ] [ weakly supervised representation learning ] [ Weak supervision ] [ Weak-supervision ] [ webly-supervised learning ] [ weight attack ] [ weight balance ] [ Weight quantization ] [ weight-sharing ] [ wide local minima ] [ Wigner-Eckart Theorem ] [ winning tickets ] [ wireframe model ] [ word-learning ] [ world models ] [ World Models ] [ worst-case generalisation ] [ xai ] [ XAI ] [ zero-order optimization ] [ zero-shot learning ] [ Zero-shot learning ] [ Zero-shot Learning ] [ Zero-shot synthesis ]

403 Results

Poster
Mon 1:00 Spatially Structured Recurrent Modules
Nasim Rahaman, Anirudh Goyal, Waleed Gondal, Manuel Wuthrich, Stefan Bauer, Yash Sharma, Yoshua Bengio, Bernhard Schoelkopf
Poster
Mon 1:00 MetaNorm: Learning to Normalize Few-Shot Batches Across Domains
Yingjun Du, Xiantong Zhen, Ling Shao, Cees G Snoek
Poster
Mon 1:00 Stabilized Medical Image Attacks
Gege Qi, Lijun GONG, Yibing Song, Kai Ma, Yefeng Zheng
Poster
Mon 1:00 Neural Jump Ordinary Differential Equations: Consistent Continuous-Time Prediction and Filtering
Calypso Herrera, Florian Krach, Josef Teichmann
Poster
Mon 1:00 Neural Approximate Sufficient Statistics for Implicit Models
Yanzhi Chen, Dinghuai Zhang, Michael U Gutmann, Aaron Courville, Zhanxing Zhu
Poster
Mon 1:00 Parameter-Based Value Functions
Francesco Faccio, Louis Kirsch, Jürgen Schmidhuber
Poster
Mon 1:00 Uncertainty Estimation and Calibration with Finite-State Probabilistic RNNs
Cheng Wang, Carolin Lawrence, Mathias Niepert
Poster
Mon 1:00 On the Universality of the Double Descent Peak in Ridgeless Regression
David Holzmüller
Poster
Mon 1:00 Towards Robust Neural Networks via Close-loop Control
Zhuotong Chen, Qianxiao Li, Zheng Zhang
Poster
Mon 1:00 Rethinking the Role of Gradient-based Attribution Methods for Model Interpretability
Suraj Srinivas, François Fleuret
Poster
Mon 1:00 Interpreting and Boosting Dropout from a Game-Theoretic View
Hao Zhang, Sen Li, YinChao Ma, Mingjie Li, Yichen Xie, Quanshi Zhang
Poster
Mon 1:00 Semantic Re-tuning with Contrastive Tension
Fredrik Carlsson, Amaru C Gyllensten, Evangelia Gogoulou, Erik Y Hellqvist, Magnus Sahlgren
Poster
Mon 1:00 Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bits
Jiawang Bai, Baoyuan Wu, Yong Zhang, Yiming Li, Zhifeng Li, Shu-Tao Xia
Poster
Mon 1:00 ResNet After All: Neural ODEs and Their Numerical Solution
Katharina Ott, Prateek Katiyar, Philipp Hennig, Michael Tiemann
Poster
Mon 1:00 PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences
Hehe Fan, Xin Yu, Yuhang Ding, Yi Yang, Mohan Kankanhalli
Poster
Mon 1:00 LEAF: A Learnable Frontend for Audio Classification
Neil Zeghidour, Olivier Teboul, Félix de Chaumont Quitry, Marco Tagliasacchi
Poster
Mon 1:00 QPLEX: Duplex Dueling Multi-Agent Q-Learning
Jianhao Wang, Zhizhou Ren, Terry Liu, Yang Yu, Chongjie Zhang
Poster
Mon 1:00 Is Label Smoothing Truly Incompatible with Knowledge Distillation: An Empirical Study
Zhiqiang Shen, Zhiqiang Shen, Dejia Xu, Zitian Chen, Kwang-Ting Cheng, Marios Savvides
Poster
Mon 1:00 Does enhanced shape bias improve neural network robustness to common corruptions?
Chaithanya Kumar Mummadi, Ranjitha Subramaniam, Robin Hutmacher, Julien Vitay, Volker Fischer, Jan Hendrik Metzen
Poster
Mon 1:00 Isometric Transformation Invariant and Equivariant Graph Convolutional Networks
Masanobu Horie, Naoki Morita, Toshiaki Hishinuma, Yu Ihara, Naoto Mitsume
Poster
Mon 1:00 Wasserstein-2 Generative Networks
Alexander Korotin, Vage Egiazarian, Arip Asadulaev, Alexander Safin, Evgeny Burnaev
Poster
Mon 1:00 Domain Generalization with MixStyle
Kaiyang Zhou, Yongxin Yang, Yu Qiao, Tao Xiang
Poster
Mon 1:00 Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch
Aojun Zhou, Yukun Ma, Junnan Zhu, Jianbo Liu, Zhijie Zhang, Kun Yuan, Wenxiu Sun, Hongsheng Li
Oral
Mon 3:00 Dataset Condensation with Gradient Matching
Bo ZHAO, Konda Reddy Mopuri, Hakan Bilen
Spotlight
Mon 3:40 Generalization in data-driven models of primary visual cortex
Konstantin-Klemens Lurz, Mohammad Bashiri, Konstantin Willeke, Akshay Jagadish, Eric Wang, Edgar Walker, Santiago Cadena Cadena, Taliah Muhammad, Erick M Cobos, Andreas Tolias, Alexander S Ecker, Fabian Sinz
Spotlight
Mon 4:30 The Intrinsic Dimension of Images and Its Impact on Learning
Phil Pope, Chen Zhu, Ahmed Abdelkader, Micah Goldblum, Tom Goldstein
Spotlight
Mon 4:40 How Benign is Benign Overfitting ?
Amartya Sanyal, Puneet Dokania, Varun Kanade, Philip Torr
Oral
Mon 5:30 Rethinking the Role of Gradient-based Attribution Methods for Model Interpretability
Suraj Srinivas, François Fleuret
Poster
Mon 9:00 Symmetry-Aware Actor-Critic for 3D Molecular Design
Gregor Simm, Robert Pinsler, Gábor Csányi, José Miguel Hernández Lobato
Poster
Mon 9:00 Teaching Temporal Logics to Neural Networks
Christopher Hahn, Frederik Schmitt, Jens Kreber, Markus Rabe, Bernd Finkbeiner
Poster
Mon 9:00 LambdaNetworks: Modeling long-range Interactions without Attention
Irwan Bello
Poster
Mon 9:00 Gradient Projection Memory for Continual Learning
Gobinda Saha, Isha Garg, Kaushik Roy
Poster
Mon 9:00 PAC Confidence Predictions for Deep Neural Network Classifiers
Sangdon Park, Shuo Li, Insup Lee, Osbert Bastani
Poster
Mon 9:00 Vector-output ReLU Neural Network Problems are Copositive Programs: Convex Analysis of Two Layer Networks and Polynomial-time Algorithms
Arda Sahiner, Tolga Ergen, John M Pauly, Mert Pilanci
Poster
Mon 9:00 Shapley Explanation Networks
Rui Wang, Xiaoqian Wang, David Inouye
Poster
Mon 9:00 Pruning Neural Networks at Initialization: Why Are We Missing the Mark?
Jonathan Frankle, Gintare Dziugaite, Anonymous A Author, Michael Carbin
Poster
Mon 9:00 LiftPool: Bidirectional ConvNet Pooling
Jiaojiao Zhao, Cees G Snoek
Poster
Mon 9:00 Scaling Symbolic Methods using Gradients for Neural Model Explanation
Subham Sahoo, Subhashini Venugopalan, Li Li, Rishabh Singh, Patrick Riley
Poster
Mon 9:00 Predicting Inductive Biases of Pre-Trained Models
Charles Lovering, Rohan Jha, Tal Linzen, Ellie Pavlick
Poster
Mon 9:00 NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation
Angtian Wang, Adam Kortylewski, Alan Yuille
Poster
Mon 9:00 On Statistical Bias In Active Learning: How and When to Fix It
Sebastian Farquhar, Yarin Gal, Tom Rainforth
Poster
Mon 9:00 Overparameterisation and worst-case generalisation: friend or foe?
Aditya Krishna Menon, Ankit Singh Rawat, Sanjiv Kumar
Poster
Mon 9:00 Universal approximation power of deep residual neural networks via nonlinear control theory
Paulo Tabuada, Bahman Gharesifard
Poster
Mon 9:00 WrapNet: Neural Net Inference with Ultra-Low-Precision Arithmetic
Renkun Ni, Hong-Min Chu, Oscar Castaneda, Ping-yeh Chiang, Christoph Studer, Tom Goldstein
Poster
Mon 9:00 A statistical theory of cold posteriors in deep neural networks
Laurence Aitchison
Poster
Mon 9:00 Shape-Texture Debiased Neural Network Training
Yinigwei Li, Qihang Yu, Mingxing Tan, Jieru Mei, Peng Tang, Wei Shen, Alan Yuille, Cihang Xie
Poster
Mon 9:00 Zero-Cost Proxies for Lightweight NAS
Mohamed Abdelfattah, Abhinav Mehrotra, Łukasz Dudziak, Nic Lane
Poster
Mon 9:00 Selectivity considered harmful: evaluating the causal impact of class selectivity in DNNs
Matthew Leavitt, Ari Morcos
Poster
Mon 9:00 Understanding the failure modes of out-of-distribution generalization
Vaishnavh Nagarajan, Anders J Andreassen, Behnam Neyshabur
Oral
Mon 11:00 Federated Learning Based on Dynamic Regularization
Durmus Alp Emre Acar, Yue Zhao, Ramon Matas, Matthew Mattina, Paul Whatmough, Venkatesh Saligrama
Oral
Mon 11:15 Gradient Projection Memory for Continual Learning
Gobinda Saha, Isha Garg, Kaushik Roy
Spotlight
Mon 12:35 Systematic generalisation with group invariant predictions
Faruk Ahmed, Yoshua Bengio, Harm van Seijen, Aaron Courville
Spotlight
Mon 12:45 On Statistical Bias In Active Learning: How and When to Fix It
Sebastian Farquhar, Yarin Gal, Tom Rainforth
Poster
Mon 17:00 MONGOOSE: A Learnable LSH Framework for Efficient Neural Network Training
Beidi Chen, Zichang Liu, Binghui Peng, Zhaozhuo Xu, Jonathan L Li, Tri Dao, Zhao Song, Anshumali Shrivastava, Christopher Re
Poster
Mon 17:00 Optimizing Memory Placement using Evolutionary Graph Reinforcement Learning
Shauharda Khadka, Estelle Aflalo, Mattias Marder, Avrech Ben-David, Santiago Miret, Shie Mannor, Tamir Hazan, Hanlin Tang, Somdeb Majumdar
Poster
Mon 17:00 Benefit of deep learning with non-convex noisy gradient descent: Provable excess risk bound and superiority to kernel methods
Taiji Suzuki, Akiyama Shunta
Poster
Mon 17:00 Federated Learning Based on Dynamic Regularization
Durmus Alp Emre Acar, Yue Zhao, Ramon Matas, Matthew Mattina, Paul Whatmough, Venkatesh Saligrama
Poster
Mon 17:00 Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks
Yige Li, Xixiang Lyu, Nodens Koren, Lingjuan Lyu, Bo Li, Daniel Ma
Poster
Mon 17:00 Incorporating Symmetry into Deep Dynamics Models for Improved Generalization
Rui Wang, Robin Walters, Rose Yu
Poster
Mon 17:00 Offline Model-Based Optimization via Normalized Maximum Likelihood Estimation
Justin Fu, Sergey Levine
Poster
Mon 17:00 On the geometry of generalization and memorization in deep neural networks
Cory Stephenson, Suchi Padhy, Abhinav Ganesh, Yue Hui, Hanlin Tang, SueYeon Chung
Poster
Mon 17:00 Robust and Generalizable Visual Representation Learning via Random Convolutions
Zhenlin Xu, Deyi Liu, Junlin Yang, Colin Raffel, Marc Niethammer
Poster
Mon 17:00 Regularization Matters in Policy Optimization - An Empirical Study on Continuous Control
Zhuang Liu, Xuanlin Li, Bingyi Kang, trevor darrell
Poster
Mon 17:00 Online Adversarial Purification based on Self-supervised Learning
Changhao Shi, Chester Holtz, Gal Mishne
Poster
Mon 17:00 Robust Curriculum Learning: from clean label detection to noisy label self-correction
Tianyi Zhou, Shengjie Wang, Jeff Bilmes
Poster
Mon 17:00 Optimal Regularization can Mitigate Double Descent
Preetum Nakkiran, Prayaag Venkat, Sham M Kakade, Tengyu Ma
Poster
Mon 17:00 Zero-shot Synthesis with Group-Supervised Learning
Yunhao Ge, Sami Abu-El-Haija, Gan Xin, Laurent Itti
Poster
Mon 17:00 Spatio-Temporal Graph Scattering Transform
Chao Pan, Siheng Chen, Antonio Ortega
Poster
Mon 17:00 When does preconditioning help or hurt generalization?
Shun-ichi Amari, Jimmy Ba, Roger Grosse, Chen Li, Atsushi Nitanda, Taiji Suzuki, Denny Wu, Ji Xu
Poster
Mon 17:00 Layer-adaptive Sparsity for the Magnitude-based Pruning
Jaeho Lee, Sejun Park, Sangwoo Mo, Sungsoo Ahn, Jinwoo Shin
Poster
Mon 17:00 MixKD: Towards Efficient Distillation of Large-scale Language Models
Kevin Liang, Weituo Hao, Dinghan Shen, Yufan Zhou, Weizhu Chen, Changyou Chen, Lawrence Carin
Poster
Mon 17:00 Score-Based Generative Modeling through Stochastic Differential Equations
Yang Song, Jascha Sohl-Dickstein, Durk Kingma, Abhishek Kumar, Stefano Ermon, Ben Poole
Poster
Mon 17:00 The Intrinsic Dimension of Images and Its Impact on Learning
Phil Pope, Chen Zhu, Ahmed Abdelkader, Micah Goldblum, Tom Goldstein
Poster
Mon 17:00 On Dyadic Fairness: Exploring and Mitigating Bias in Graph Connections
Peizhao Li, Yifei Wang, Han Zhao, Pengyu Hong, Hongfu Liu
Poster
Mon 17:00 Sequential Density Ratio Estimation for Simultaneous Optimization of Speed and Accuracy
Akinori Ebihara, Taiki Miyagawa, Kazuyuki Sakurai, Hitoshi Imaoka
Poster
Mon 17:00 One Network Fits All? Modular versus Monolithic Task Formulations in Neural Networks
Atish Agarwala, Abhimanyu Das, Brendan Juba, Rina Panigrahy, Vatsal Sharan, Xin Wang, Qiuyi Zhang
Poster
Mon 17:00 SAFENet: A Secure, Accurate and Fast Neural Network Inference
Qian Lou, Yilin Shen, Hongxia Jin, Lei Jiang
Spotlight
Mon 20:18 Improving Adversarial Robustness via Channel-wise Activation Suppressing
Yang Bai, Yuyuan Zeng, Yong Jiang, Shu-Tao Xia, Daniel Ma, Yisen Wang
Spotlight
Mon 20:28 Fast Geometric Projections for Local Robustness Certification
Aymeric Fromherz, Klas Leino, Matt Fredrikson, Bryan Parno, Corina Pasareanu
Spotlight
Mon 20:58 HW-NAS-Bench: Hardware-Aware Neural Architecture Search Benchmark
Chaojian Li, Zhongzhi Yu, Yonggan Fu, Yongan Zhang, Yang Zhao, Haoran You, Qixuan Yu, Yue Wang, Cong Hao, Yingyan Lin
Oral
Mon 21:21 How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks
Keyulu Xu, Mozhi Zhang, Jingling Li, Simon Du, Ken-Ichi Kawarabayashi, Stefanie Jegelka
Invited Talk
Tue 0:00 Geometric Deep Learning: the Erlangen Programme of ML
Michael Bronstein
Poster
Tue 1:00 Auxiliary Learning by Implicit Differentiation
Aviv Navon, Idan Achituve, Haggai Maron, Gal Chechik, Ethan Fetaya
Poster
Tue 1:00 Computational Separation Between Convolutional and Fully-Connected Networks
Eran Malach, Shai Shalev-Shwartz
Poster
Tue 1:00 Spatial Dependency Networks: Neural Layers for Improved Generative Image Modeling
Đorđe Miladinović, Aleksandar Stanić, Stefan Bauer, Jürgen Schmidhuber, Joachim M Buhmann
Poster
Tue 1:00 Generalization in data-driven models of primary visual cortex
Konstantin-Klemens Lurz, Mohammad Bashiri, Konstantin Willeke, Akshay Jagadish, Eric Wang, Edgar Walker, Santiago Cadena Cadena, Taliah Muhammad, Erick M Cobos, Andreas Tolias, Alexander S Ecker, Fabian Sinz
Poster
Tue 1:00 Hyperbolic Neural Networks++
Ryohei Shimizu, YUSUKE Mukuta, Tatsuya Harada
Poster
Tue 1:00 Activation-level uncertainty in deep neural networks
Pablo Morales-Alvarez, Daniel Hernández-Lobato, Rafael Molina, José Miguel Hernández Lobato
Poster
Tue 1:00 Intraclass clustering: an implicit learning ability that regularizes DNNs
Simon Carbonnelle, Christophe De Vleeschouwer
Poster
Tue 1:00 Scaling the Convex Barrier with Active Sets
Alessandro De Palma, Harkirat Singh Behl, Rudy R Bunel, Philip Torr, M. Pawan Kumar
Poster
Tue 1:00 A Block Minifloat Representation for Training Deep Neural Networks
Sean Fox, Seyedramin Rasoulinezhad, Julian Faraone, david boland, Philip Leong
Poster
Tue 1:00 Learning Incompressible Fluid Dynamics from Scratch - Towards Fast, Differentiable Fluid Models that Generalize
Nils Wandel, Michael Weinmann, Reinhard Klein
Poster
Tue 1:00 Winning the L2RPN Challenge: Power Grid Management via Semi-Markov Afterstate Actor-Critic
Deunsol Yoon, Sunghoon Hong, Byung-Jun Lee, Kee-Eung Kim
Poster
Tue 1:00 SkipW: Resource Adaptable RNN with Strict Upper Computational Limit
Tsiry MAYET, Anne Lambert, Pascal Le Guyadec, Francoise Le Bolzer, François Schnitzler
Poster
Tue 1:00 Neurally Augmented ALISTA
Freya Behrens, Jonathan Sauder, Peter Jung
Poster
Tue 1:00 Learning Accurate Entropy Model with Global Reference for Image Compression
Yichen Qian, Zhiyu Tan, Xiuyu Sun, Ming Lin, Dongyang Li, Zhenhong Sun, Li Hao, Rong Jin
Poster
Tue 1:00 Effective Abstract Reasoning with Dual-Contrast Network
Tao Zhuo, Mohan Kankanhalli
Poster
Tue 1:00 not-MIWAE: Deep Generative Modelling with Missing not at Random Data
Niels Ipsen, Pierre-Alexandre Mattei, Jes Frellsen
Poster
Tue 1:00 Learning Better Structured Representations Using Low-rank Adaptive Label Smoothing
Asish Ghoshal, Xilun Chen, Sonal Gupta, Luke Zettlemoyer, Yashar Mehdad
Poster
Tue 1:00 Lossless Compression of Structured Convolutional Models via Lifting
Gustav Sourek, Filip Zelezny, Ondrej Kuzelka
Poster
Tue 1:00 Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering
Yuxuan Zhang, Wenzheng Chen, Huan Ling, Jun Gao, Yinan Zhang, Antonio Torralba, Sanja Fidler
Poster
Tue 1:00 Conformation-Guided Molecular Representation with Hamiltonian Neural Networks
Ziyao Li, Shuwen Yang, Guojie Song, Lingsheng Cai
Poster
Tue 1:00 A Trainable Optimal Transport Embedding for Feature Aggregation and its Relationship to Attention
Grégoire Mialon, Dexiong Chen, Alexandre d'Aspremont, Julien Mairal
Poster
Tue 1:00 Exemplary Natural Images Explain CNN Activations Better than State-of-the-Art Feature Visualization
Judy Borowski, Roland Zimmermann, Judith Schepers, Robert Geirhos, Thomas S Wallis, Matthias Bethge, Wieland Brendel
Poster
Tue 1:00 Accurate Learning of Graph Representations with Graph Multiset Pooling
Jinheon Baek, Minki Kang, Sung Ju Hwang
Poster
Tue 1:00 Large-width functional asymptotics for deep Gaussian neural networks
Daniele Bracale, Stefano Favaro, Sandra Fortini, Stefano Peluchetti
Poster
Tue 1:00 AdaGCN: Adaboosting Graph Convolutional Networks into Deep Models
Ke Sun, Zhanxing Zhu, Zhouchen Lin
Poster
Tue 1:00 Identifying nonlinear dynamical systems with multiple time scales and long-range dependencies
Dominik Schmidt, Georgia Koppe, Zahra Monfared, Max Beutelspacher, Daniel Durstewitz
Poster
Tue 1:00 Practical Real Time Recurrent Learning with a Sparse Approximation
Jacob Menick, Erich Elsen, Utku Evci, Simon Osindero, Karen Simonyan, Alex Graves
Spotlight
Tue 3:25 Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking
Michael Schlichtkrull, Nicola De Cao, Ivan Titov
Spotlight
Tue 3:35 Expressive Power of Invariant and Equivariant Graph Neural Networks
Waïss Azizian, marc lelarge
Spotlight
Tue 5:18 Learning Incompressible Fluid Dynamics from Scratch - Towards Fast, Differentiable Fluid Models that Generalize
Nils Wandel, Michael Weinmann, Reinhard Klein
Spotlight
Tue 5:28 Identifying nonlinear dynamical systems with multiple time scales and long-range dependencies
Dominik Schmidt, Georgia Koppe, Zahra Monfared, Max Beutelspacher, Daniel Durstewitz
Poster
Tue 9:00 Reducing the Computational Cost of Deep Generative Models with Binary Neural Networks
Thomas Bird, Friso Kingma, David Barber
Poster
Tue 9:00 NOVAS: Non-convex Optimization via Adaptive Stochastic Search for End-to-end Learning and Control
Ioannis Exarchos, Marcus A Pereira, Ziyi Wang, Evangelos Theodorou
Poster
Tue 9:00 Teaching with Commentaries
Aniruddh Raghu, Maithra Raghu, Simon Kornblith, David Duvenaud, Geoffrey Hinton
Poster
Tue 9:00 Learning from Protein Structure with Geometric Vector Perceptrons
Bowen Jing, Stephan Eismann, Patricia Suriana, Raphael J Townshend, Ron Dror
Poster
Tue 9:00 Getting a CLUE: A Method for Explaining Uncertainty Estimates
Javier Antorán, Umang Bhatt, Tameem Adel, Adrian Weller, José Miguel Hernández Lobato
Poster
Tue 9:00 DialoGraph: Incorporating Interpretable Strategy-Graph Networks into Negotiation Dialogues
Rishabh Joshi, Vidhisha Balachandran, Shikhar Vashishth, Alan Black, Yulia Tsvetkov
Poster
Tue 9:00 On the Dynamics of Training Attention Models
Haoye Lu, Yongyi Mao, Amiya Nayak
Poster
Tue 9:00 Single-Timescale Actor-Critic Provably Finds Globally Optimal Policy
Zuyue Fu, Zhuoran Yang, Zhaoran Wang
Poster
Tue 9:00 Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNs
Jonathan Frankle, David J Schwab, Ari Morcos
Poster
Tue 9:00 Are wider nets better given the same number of parameters?
Anna Golubeva, Guy Gur-Ari, Behnam Neyshabur
Poster
Tue 9:00 Robust Pruning at Initialization
Soufiane Hayou, Jean-Francois Ton, Arnaud Doucet, Yee Whye Teh
Poster
Tue 9:00 Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics
Vinay Ramasesh, Ethan Dyer, Maithra Raghu
Poster
Tue 9:00 Mapping the Timescale Organization of Neural Language Models
Hsiang-Yun Sherry Chien, Jinhan Zhang, Christopher Honey
Poster
Tue 9:00 Learning Parametrised Graph Shift Operators
George Dasoulas, Johannes Lutzeyer, Michalis Vazirgiannis
Poster
Tue 9:00 Understanding Over-parameterization in Generative Adversarial Networks
Yogesh Balaji, Mohammadmahdi Sajedi, Neha Kalibhat, Mucong Ding, Dominik Stöger, Mahdi Soltanolkotabi, Soheil Feizi
Poster
Tue 9:00 Tradeoffs in Data Augmentation: An Empirical Study
Rapha Gontijo Lopes, Sylvia Smullin, Ekin Cubuk, Ethan Dyer
Poster
Tue 9:00 Auction Learning as a Two-Player Game
Jad Rahme, Samy Jelassi, S. M Weinberg
Poster
Tue 9:00 How Benign is Benign Overfitting ?
Amartya Sanyal, Puneet Dokania, Varun Kanade, Philip Torr
Poster
Tue 9:00 Global optimality of softmax policy gradient with single hidden layer neural networks in the mean-field regime
Andrea Agazzi, Jianfeng Lu
Poster
Tue 9:00 UMEC: Unified model and embedding compression for efficient recommendation systems
Jiayi Shen, Haotao Wang, Shupeng Gui, Jianchao Tan, Zhangyang Wang, Ji Liu
Poster
Tue 9:00 Shape or Texture: Understanding Discriminative Features in CNNs
Md Amirul Islam, Matthew Kowal, Patrick Esser, Sen Jia, Björn Ommer, Kosta Derpanis, Neil Bruce
Poster
Tue 9:00 SSD: A Unified Framework for Self-Supervised Outlier Detection
Vikash Sehwag, Mung Chiang, Prateek Mittal
Poster
Tue 9:00 The geometry of integration in text classification RNNs
Kyle Aitken, Vinay Ramasesh, Ankush Garg, Yuan Cao, David Sussillo, Niru Maheswaranathan
Poster
Tue 9:00 Transient Non-stationarity and Generalisation in Deep Reinforcement Learning
Maximilian Igl, Gregory Farquhar, Jelena Luketina, Wendelin Boehmer, Shimon Whiteson
Poster
Tue 9:00 Characterizing signal propagation to close the performance gap in unnormalized ResNets
Andrew Brock, Soham De, Samuel Smith
Poster
Tue 9:00 Systematic generalisation with group invariant predictions
Faruk Ahmed, Yoshua Bengio, Harm van Seijen, Aaron Courville
Poster
Tue 9:00 Distance-Based Regularisation of Deep Networks for Fine-Tuning
Henry Gouk, Timothy Hospedales, massimiliano pontil
Oral
Tue 12:00 Randomized Automatic Differentiation
Deniz Oktay, Nick McGreivy, Joshua Aduol, Alex Beatson, Ryan P Adams
Oral
Tue 12:15 Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering
Yuxuan Zhang, Wenzheng Chen, Huan Ling, Jun Gao, Yinan Zhang, Antonio Torralba, Sanja Fidler
Spotlight
Tue 12:40 Implicit Convex Regularizers of CNN Architectures: Convex Optimization of Two- and Three-Layer Networks in Polynomial Time
Tolga Ergen, Mert Pilanci
Spotlight
Tue 12:50 Learning from Protein Structure with Geometric Vector Perceptrons
Bowen Jing, Stephan Eismann, Patricia Suriana, Raphael J Townshend, Ron Dror
Poster
Tue 17:00 Fuzzy Tiling Activations: A Simple Approach to Learning Sparse Representations Online
Yangchen Pan, Kirby Banman, Martha White
Poster
Tue 17:00 Generalized Variational Continual Learning
Noel Loo, Siddharth Swaroop, Rich E Turner
Poster
Tue 17:00 Contextual Dropout: An Efficient Sample-Dependent Dropout Module
XINJIE FAN, Shujian Zhang, Korawat Tanwisuth, Xiaoning Qian, Mingyuan Zhou
Poster
Tue 17:00 A Temporal Kernel Approach for Deep Learning with Continuous-time Information
Da Xu, Chuanwei Ruan, evren korpeoglu, Sushant Kumar, kannan achan
Poster
Tue 17:00 DDPNOpt: Differential Dynamic Programming Neural Optimizer
Guan-Horng Liu, Tianrong Chen, Evangelos Theodorou
Poster
Tue 17:00 Fantastic Four: Differentiable and Efficient Bounds on Singular Values of Convolution Layers
ssingla Singla, Soheil Feizi
Poster
Tue 17:00 Discovering Non-monotonic Autoregressive Orderings with Variational Inference
Xuanlin Li, Brandon Trabucco, Dong Huk Park, Michael Luo, Sheng Shen, trevor darrell, Yang Gao
Poster
Tue 17:00 Convex Potential Flows: Universal Probability Distributions with Optimal Transport and Convex Optimization
Chin-Wei Huang, Ricky T. Q. Chen, Christos Tsirigotis, Aaron Courville
Poster
Tue 17:00 Attentional Constellation Nets for Few-Shot Learning
Weijian Xu, Yifan Xu, Huaijin Wang, Zhuowen Tu
Poster
Tue 17:00 Drop-Bottleneck: Learning Discrete Compressed Representation for Noise-Robust Exploration
Jaekyeom Kim, Minjung Kim, Dongyeon Woo, Gunhee Kim
Poster
Tue 17:00 Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability
Jeremy Cohen, Simran Kaur, Yuanzhi Li, Zico Kolter, Ameet Talwalkar
Poster
Tue 17:00 Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity
Jang-Hyun Kim, Wonho Choo, Hosan Jeong, Hyun Oh Song
Poster
Tue 17:00 CopulaGNN: Towards Integrating Representational and Correlational Roles of Graphs in Graph Neural Networks
Jiaqi Ma, Bo Chang, Xuefei Zhang, Qiaozhu Mei
Poster
Tue 17:00 Multi-resolution modeling of a discrete stochastic process identifies causes of cancer
Adam Yaari, Maxwell Sherman, Oliver C Priebe, Po-Ru Loh, Boris Katz, Andrei Barbu, Bonnie Berger
Poster
Tue 17:00 A unifying view on implicit bias in training linear neural networks
Chulhee (Charlie) Yun, Shankar Krishnan, Hossein Mobahi
Poster
Tue 17:00 Learning Safe Multi-agent Control with Decentralized Neural Barrier Certificates
Zengyi Qin, Kaiqing Zhang, chenyx Chen, Jingkai Chen, Chuchu Fan
Poster
Tue 17:00 SEDONA: Search for Decoupled Neural Networks toward Greedy Block-wise Learning
Myeongjang Pyeon, Jihwan Moon, Taeyoung Hahn, Gunhee Kim
Poster
Tue 17:00 Lipschitz Recurrent Neural Networks
N. Benjamin Erichson, Omri Azencot, Alejandro Queiruga, Liam Hodgkinson, Michael W Mahoney
Poster
Tue 17:00 Implicit Convex Regularizers of CNN Architectures: Convex Optimization of Two- and Three-Layer Networks in Polynomial Time
Tolga Ergen, Mert Pilanci
Poster
Tue 17:00 FedBE: Making Bayesian Model Ensemble Applicable to Federated Learning
Hong-You Chen, Wei-Lun Chao
Poster
Tue 17:00 HalentNet: Multimodal Trajectory Forecasting with Hallucinative Intents
Deyao Zhu, Mohamed Zahran, Li Erran Li, Mohamed Elhoseiny
Poster
Tue 17:00 How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision
Dongkwan Kim, Alice Oh
Poster
Tue 17:00 How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks
Keyulu Xu, Mozhi Zhang, Jingling Li, Simon Du, Ken-Ichi Kawarabayashi, Stefanie Jegelka
Poster
Tue 17:00 Fourier Neural Operator for Parametric Partial Differential Equations
Zongyi Li, Nikola B Kovachki, Kamyar Azizzadenesheli, Burigede liu, Kaushik Bhattacharya, Andrew Stuart, Anima Anandkumar
Poster
Tue 17:00 Linear Mode Connectivity in Multitask and Continual Learning
Seyed Iman Mirzadeh, Mehrdad Farajtabar, Dilan Gorur, Razvan Pascanu, Hassan Ghasemzadeh
Poster
Tue 17:00 Why Are Convolutional Nets More Sample-Efficient than Fully-Connected Nets?
Zhiyuan Li, Yi Zhang, Sanjeev Arora
Poster
Tue 17:00 BUSTLE: Bottom-Up Program Synthesis Through Learning-Guided Exploration
Augustus Odena, Kensen Shi, David Bieber, Rishabh Singh, Charles Sutton, Hanjun Dai
Poster
Tue 17:00 Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning
Aviral Kumar, Rishabh Agarwal, Dibya Ghosh, Sergey Levine
Poster
Tue 17:00 Neural Mechanics: Symmetry and Broken Conservation Laws in Deep Learning Dynamics
Daniel Kunin, Javier Sagastuy-Brena, Surya Ganguli, Daniel L Yamins, Hidenori Tanaka
Poster
Tue 17:00 Do Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width and Depth
Thao Nguyen, Maithra Raghu, Simon Kornblith
Poster
Tue 17:00 On Graph Neural Networks versus Graph-Augmented MLPs
Lei Chen, Zhengdao Chen, Joan Bruna
Poster
Tue 17:00 A Discriminative Gaussian Mixture Model with Sparsity
Hideaki Hayashi, Seiichi Uchida
Poster
Tue 17:00 Discrete Graph Structure Learning for Forecasting Multiple Time Series
Chao Shang, Jie Chen, Jinbo Bi
Poster
Tue 17:00 Are Neural Rankers still Outperformed by Gradient Boosted Decision Trees?
Zhen Qin, Le Yan, Honglei Zhuang, Yi Tay, Rama Kumar Pasumarthi, Xuanhui Wang, Michael Bendersky, Marc Najork
Oral
Tue 19:00 Deep symbolic regression: Recovering mathematical expressions from data via risk-seeking policy gradients
Brenden Petersen, Mikel Landajuela Larma, Terrell N Mundhenk, Claudio Santiago, Soo Kim, Joanne Kim
Spotlight
Tue 19:15 DDPNOpt: Differential Dynamic Programming Neural Optimizer
Guan-Horng Liu, Tianrong Chen, Evangelos Theodorou
Oral
Tue 19:55 Global Convergence of Three-layer Neural Networks in the Mean Field Regime
Huy Tuan Pham, Phan-Minh Nguyen
Spotlight
Tue 20:10 Minimum Width for Universal Approximation
Sejun Park, Chulhee (Charlie) Yun, Jaeho Lee, Jinwoo Shin
Spotlight
Tue 20:40 Are Neural Rankers still Outperformed by Gradient Boosted Decision Trees?
Zhen Qin, Le Yan, Honglei Zhuang, Yi Tay, Rama Kumar Pasumarthi, Xuanhui Wang, Michael Bendersky, Marc Najork
Oral
Tue 21:03 Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity
Jang-Hyun Kim, Wonho Choo, Hosan Jeong, Hyun Oh Song
Oral
Tue 21:18 MONGOOSE: A Learnable LSH Framework for Efficient Neural Network Training
Beidi Chen, Zichang Liu, Binghui Peng, Zhaozhuo Xu, Jonathan L Li, Tri Dao, Zhao Song, Anshumali Shrivastava, Christopher Re
Spotlight
Tue 21:33 Locally Free Weight Sharing for Network Width Search
Xiu Su, Shan You, Tao Huang, Fei Wang, Chen Qian, Changshui Zhang, Chang Xu
Poster
Wed 1:00 Neural ODE Processes
Alexander Norcliffe, Cristian Bodnar, Ben Day, Jacob Moss, Pietro Liò
Poster
Wed 1:00 IEPT: Instance-Level and Episode-Level Pretext Tasks for Few-Shot Learning
Manli Zhang, Jianhong Zhang, Zhiwu Lu, Tao Xiang, Mingyu Ding, Songfang Huang
Poster
Wed 1:00 Improving Adversarial Robustness via Channel-wise Activation Suppressing
Yang Bai, Yuyuan Zeng, Yong Jiang, Shu-Tao Xia, Daniel Ma, Yisen Wang
Poster
Wed 1:00 Locally Free Weight Sharing for Network Width Search
Xiu Su, Shan You, Tao Huang, Fei Wang, Chen Qian, Changshui Zhang, Chang Xu
Poster
Wed 1:00 Separation and Concentration in Deep Networks
John Zarka, Florentin Guth, Stéphane Mallat
Poster
Wed 1:00 Deep Neural Network Fingerprinting by Conferrable Adversarial Examples
Nils Lukas, Yuxuan Zhang, Florian Kerschbaum
Poster
Wed 1:00 Neural networks with late-phase weights
Johannes von Oswald, Seijin Kobayashi, Joao Sacramento, Alexander Meulemans, Christian Henning, Benjamin F Grewe
Poster
Wed 1:00 Removing Undesirable Feature Contributions Using Out-of-Distribution Data
Saehyung Lee, Changhwa Park, Hyungyu Lee, Jihun Yi, Jonghyun Lee, Sungroh Yoon
Poster
Wed 1:00 Learning Associative Inference Using Fast Weight Memory
Imanol Schlag, Tsendsuren Munkhdalai, Jürgen Schmidhuber
Poster
Wed 1:00 Degree-Quant: Quantization-Aware Training for Graph Neural Networks
Shyam Tailor, Javier Fernandez-Marques, Nic Lane
Poster
Wed 1:00 Net-DNF: Effective Deep Modeling of Tabular Data
Liran Katzir, Gal Elidan, Ran El-Yaniv
Poster
Wed 1:00 Grounded Language Learning Fast and Slow
Felix Hill, Olivier Tieleman, Tamara von Glehn, Nathaniel Wong, Hamza Merzic, Stephen Clark
Poster
Wed 1:00 Efficient Continual Learning with Modular Networks and Task-Driven Priors
Tom Veniat, Ludovic Denoyer, Marc'Aurelio Ranzato
Poster
Wed 1:00 BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction
Yuhang Li, Ruihao Gong, Xu Tan, Yang Yang, Peng Hu, Qi Zhang, fengwei yu, Wei Wang, Shi Gu
Poster
Wed 1:00 Simple Spectral Graph Convolution
Hao Zhu, Piotr Koniusz
Poster
Wed 1:00 Neural Delay Differential Equations
Qunxi Zhu, Yao Guo, Wei Lin
Poster
Wed 1:00 Graph Edit Networks
Benjamin Paassen, Daniele Grattarola, Daniele Zambon, Cesare Alippi, Barbara E Hammer
Poster
Wed 1:00 Reweighting Augmented Samples by Minimizing the Maximal Expected Loss
Mingyang Yi, LU HOU, Lifeng Shang, Xin Jiang, Qun Liu, Zhi-Ming Ma
Poster
Wed 1:00 Expressive Power of Invariant and Equivariant Graph Neural Networks
Waïss Azizian, marc lelarge
Poster
Wed 1:00 Learning from Demonstration with Weakly Supervised Disentanglement
Yordan Hristov, Subramanian Ramamoorthy
Poster
Wed 1:00 Fooling a Complete Neural Network Verifier
Dániel Zombori, Balázs Bánhelyi, Tibor Csendes, István Megyeri, Márk Jelasity
Poster
Wed 1:00 Dance Revolution: Long-Term Dance Generation with Music via Curriculum Learning
Ruozi Huang, Huang Hu, Wei Wu, Kei Sawada, Mi Zhang, Daxin Jiang
Poster
Wed 1:00 A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference
Sanghyun Hong, Yigitcan Kaya, Ionut-Vlad Modoranu, Tudor Dumitras
Poster
Wed 1:00 Byzantine-Resilient Non-Convex Stochastic Gradient Descent
Zeyuan Allen-Zhu, Faeze Ebrahimianghazani, Jerry Li, Dan Alistarh
Oral
Wed 4:05 Getting a CLUE: A Method for Explaining Uncertainty Estimates
Javier Antorán, Umang Bhatt, Tameem Adel, Adrian Weller, José Miguel Hernández Lobato
Spotlight
Wed 4:30 Stabilized Medical Image Attacks
Gege Qi, Lijun GONG, Yibing Song, Kai Ma, Yefeng Zheng
Spotlight
Wed 4:40 Deep Neural Network Fingerprinting by Conferrable Adversarial Examples
Nils Lukas, Yuxuan Zhang, Florian Kerschbaum
Spotlight
Wed 5:15 Benefit of deep learning with non-convex noisy gradient descent: Provable excess risk bound and superiority to kernel methods
Taiji Suzuki, Akiyama Shunta
Spotlight
Wed 5:35 Neural Approximate Sufficient Statistics for Implicit Models
Yanzhi Chen, Dinghuai Zhang, Michael U Gutmann, Aaron Courville, Zhanxing Zhu
Wed 6:00 Panel discussion on model efficiency and quantization
Poster
Wed 9:00 Anchor & Transform: Learning Sparse Embeddings for Large Vocabularies
Paul Pu Liang, Manzil Zaheer, Yuan Wang, Amr Ahmed
Poster
Wed 9:00 PC2WF: 3D Wireframe Reconstruction from Raw Point Clouds
Yujia Liu, Stefano D'Aronco, Konrad Schindler, Jan D Wegner
Poster
Wed 9:00 Graph Information Bottleneck for Subgraph Recognition
Junchi Yu, Tingyang Xu, Yu Rong, Yatao Bian, Junzhou Huang, Ran He
Poster
Wed 9:00 On the Bottleneck of Graph Neural Networks and its Practical Implications
Uri Alon, Eran Yahav
Poster
Wed 9:00 TropEx: An Algorithm for Extracting Linear Terms in Deep Neural Networks
Martin Trimmel, Henning Petzka, Cristian Sminchisescu
Poster
Wed 9:00 Continuous Wasserstein-2 Barycenter Estimation without Minimax Optimization
Alexander Korotin, Lingxiao Li, Justin Solomon, Evgeny Burnaev
Poster
Wed 9:00 Learning Mesh-Based Simulation with Graph Networks
Tobias Pfaff, Meire Fortunato, Alvaro Sanchez Gonzalez, Peter Battaglia
Poster
Wed 9:00 Boost then Convolve: Gradient Boosting Meets Graph Neural Networks
Sergei Ivanov, Liudmila Prokhorenkova
Poster
Wed 9:00 Differentiable Trust Region Layers for Deep Reinforcement Learning
Fabian Otto, Philipp Becker, Vien A Ngo, Hanna Ziesche, Gerhard Neumann
Poster
Wed 9:00 Neural Networks for Learning Counterfactual G-Invariances from Single Environments
S Chandra Mouli, Bruno Ribeiro
Poster
Wed 9:00 Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking
Michael Schlichtkrull, Nicola De Cao, Ivan Titov
Poster
Wed 9:00 Perceptual Adversarial Robustness: Defense Against Unseen Threat Models
Cassidy Laidlaw, ssingla Singla, Soheil Feizi
Poster
Wed 9:00 Multiplicative Filter Networks
Rizal Fathony, Anit Kumar Sahu, Devin Willmott, Zico Kolter
Poster
Wed 9:00 Early Stopping in Deep Networks: Double Descent and How to Eliminate it
Reinhard Heckel, Fatih Furkan Yilmaz
Poster
Wed 9:00 Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks
Robert Csordas, Sjoerd van Steenkiste, Jürgen Schmidhuber
Poster
Wed 9:00 Exploring the Uncertainty Properties of Neural Networks’ Implicit Priors in the Infinite-Width Limit
Ben Adlam, Jaehoon Lee, Lechao Xiao, Jeffrey Pennington, Jasper Snoek
Poster
Wed 9:00 My Body is a Cage: the Role of Morphology in Graph-Based Incompatible Control
Vitaly Kurin, Maximilian Igl, Tim Rocktaeschel, Wendelin Boehmer, Shimon Whiteson
Poster
Wed 9:00 More or Less: When and How to Build Convolutional Neural Network Ensembles
Abdul Wasay, Stratos Idreos
Poster
Wed 9:00 Learning Task-General Representations with Generative Neuro-Symbolic Modeling
Reuben Feinman, Brenden Lake
Poster
Wed 9:00 Learning advanced mathematical computations from examples
François Charton, Amaury Hayat, Guillaume Lample
Poster
Wed 9:00 Variational State-Space Models for Localisation and Dense 3D Mapping in 6 DoF
Atanas Mirchev, Baris Kayalibay, Patrick van der Smagt, Justin Bayer
Poster
Wed 9:00 Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching
Jonas Geiping, Liam H Fowl, Ronny Huang, Wojciech Czaja, Gavin Taylor, Michael Moeller, Tom Goldstein
Poster
Wed 9:00 Training independent subnetworks for robust prediction
Marton Havasi, Rodolphe Jenatton, Stanislav Fort, Jeremiah Zhe Liu, Jasper Snoek, Balaji Lakshminarayanan, Andrew Dai, Dustin Tran
Poster
Wed 9:00 Deep symbolic regression: Recovering mathematical expressions from data via risk-seeking policy gradients
Brenden Petersen, Mikel Landajuela Larma, Terrell N Mundhenk, Claudio Santiago, Soo Kim, Joanne Kim
Poster
Wed 9:00 Probabilistic Numeric Convolutional Neural Networks
Marc Finzi, Roberto Bondesan, Max Welling
Poster
Wed 9:00 Entropic gradient descent algorithms and wide flat minima
Fabrizio Pittorino, Carlo Lucibello, Christoph Feinauer, Gabriele Perugini, Carlo Baldassi, Elizaveta Demyanenko, Riccardo Zecchina
Poster
Wed 9:00 Coupled Oscillatory Recurrent Neural Network (coRNN): An accurate and (gradient) stable architecture for learning long time dependencies
T. Konstantin Rusch, Siddhartha Mishra
Oral
Wed 12:23 Coupled Oscillatory Recurrent Neural Network (coRNN): An accurate and (gradient) stable architecture for learning long time dependencies
T. Konstantin Rusch, Siddhartha Mishra
Spotlight
Wed 12:38 Sequential Density Ratio Estimation for Simultaneous Optimization of Speed and Accuracy
Akinori Ebihara, Taiki Miyagawa, Kazuyuki Sakurai, Hitoshi Imaoka
Spotlight
Wed 12:48 LambdaNetworks: Modeling long-range Interactions without Attention
Irwan Bello
Spotlight
Wed 12:58 Grounded Language Learning Fast and Slow
Felix Hill, Olivier Tieleman, Tamara von Glehn, Nathaniel Wong, Hamza Merzic, Stephen Clark
Spotlight
Wed 13:58 Differentially Private Learning Needs Better Features (or Much More Data)
Florian Tramer, Dan Boneh
Oral
Wed 16:15 EigenGame: PCA as a Nash Equilibrium
Ian Gemp, Brian McWilliams, Claire Vernade, Thore Graepel
Oral
Wed 16:30 Score-Based Generative Modeling through Stochastic Differential Equations
Yang Song, Jascha Sohl-Dickstein, Durk Kingma, Abhishek Kumar, Stefano Ermon, Ben Poole
Spotlight
Wed 16:45 Learning Mesh-Based Simulation with Graph Networks
Tobias Pfaff, Meire Fortunato, Alvaro Sanchez Gonzalez, Peter Battaglia
Poster
Wed 17:00 Economic Hyperparameter Optimization With Blended Search Strategy
Chi Wang, Qingyun Wu, Silu Huang, Amin Saied
Poster
Wed 17:00 CPR: Classifier-Projection Regularization for Continual Learning
Sungmin Cha, Hsiang Hsu, Taebaek Hwang, Flavio Calmon, Taesup Moon
Poster
Wed 17:00 Learning with Instance-Dependent Label Noise: A Sample Sieve Approach
Hao Cheng, Zhaowei Zhu, Xingyu Li, Yifei Gong, Xing Sun, Yang Liu
Poster
Wed 17:00 Efficient Empowerment Estimation for Unsupervised Stabilization
Ruihan Zhao, Kevin Lu, Pieter Abbeel, Stas Tiomkin
Poster
Wed 17:00 Adaptive Universal Generalized PageRank Graph Neural Network
Eli Chien, Jianhao Peng, Pan Li, Olgica Milenkovic
Poster
Wed 17:00 Learning Manifold Patch-Based Representations of Man-Made Shapes
Dmitriy Smirnov, Mikhail Bessmeltsev, Justin Solomon
Poster
Wed 17:00 Estimating informativeness of samples with Smooth Unique Information
Hrayr Harutyunyan, Alessandro Achille, Giovanni Paolini, Orchid Majumder, Avinash Ravichandran, Rahul Bhotika, Stefano Soatto
Poster
Wed 17:00 NBDT: Neural-Backed Decision Tree
Alvin Wan, Lisa Dunlap, Daniel Ho, Jihan Yin, Scott Lee, Suzanne Petryk, Sarah A Bargal, Joseph E Gonzalez
Poster
Wed 17:00 INT: An Inequality Benchmark for Evaluating Generalization in Theorem Proving
Yuhuai Wu, Albert Jiang, Jimmy Ba, Roger Grosse
Poster
Wed 17:00 Protecting DNNs from Theft using an Ensemble of Diverse Models
Sanjay Kariyappa, Atul Prakash, Moinuddin K Qureshi
Poster
Wed 17:00 Emergent Symbols through Binding in External Memory
Taylor Webb, Ishan Sinha, Jonathan Cohen
Poster
Wed 17:00 Influence Functions in Deep Learning Are Fragile
Samyadeep Basu, Phil Pope, Soheil Feizi
Poster
Wed 17:00 Effective and Efficient Vote Attack on Capsule Networks
Jindong Gu, Baoyuan Wu, Volker Tresp
Poster
Wed 17:00 Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective
Wuyang Chen, Xinyu Gong, Zhangyang Wang
Poster
Wed 17:00 A PAC-Bayesian Approach to Generalization Bounds for Graph Neural Networks
Renjie Liao, Raquel Urtasun, Richard Zemel
Poster
Wed 17:00 Explainable Subgraph Reasoning for Forecasting on Temporal Knowledge Graphs
Zhen Han, Peng Chen, Yunpu Ma, Volker Tresp
Poster
Wed 17:00 Combining Physics and Machine Learning for Network Flow Estimation
Arlei Lopes da Silva, Furkan Kocayusufoglu, Saber Jafarpour, Francesco Bullo, Ananthram Swami, Ambuj K Singh
Poster
Wed 17:00 Simple Augmentation Goes a Long Way: ADRL for DNN Quantization
Lin Ning, Guoyang Chen, Weifeng Zhang, Xipeng Shen
Spotlight
Wed 19:35 Emergent Symbols through Binding in External Memory
Taylor Webb, Ishan Sinha, Jonathan Cohen
Spotlight
Wed 20:50 CPT: Efficient Deep Neural Network Training via Cyclic Precision
Yonggan Fu, Han Guo, Meng Li, Xin Yang, Yining Ding, Vikas Chandra, Yingyan Lin
Spotlight
Wed 21:25 Regularization Matters in Policy Optimization - An Empirical Study on Continuous Control
Zhuang Liu, Xuanlin Li, Bingyi Kang, trevor darrell
Oral
Thu 0:30 Optimal Rates for Averaged Stochastic Gradient Descent under Neural Tangent Kernel Regime
Atsushi Nitanda, Taiji Suzuki
Poster
Thu 1:00 Interpretable Models for Granger Causality Using Self-explaining Neural Networks
Ričards Marcinkevičs, Julia E Vogt
Poster
Thu 1:00 R-GAP: Recursive Gradient Attack on Privacy
Junyi Zhu, Matthew Blaschko
Poster
Thu 1:00 Understanding the effects of data parallelism and sparsity on neural network training
Namhoon Lee, Thalaiyasingam Ajanthan, Philip Torr, Martin Jaggi
Poster
Thu 1:00 Continual learning in recurrent neural networks
Benjamin Ehret, Christian Henning, Maria Cervera, Alexander Meulemans, Johannes von Oswald, Benjamin F Grewe
Poster
Thu 1:00 Learning continuous-time PDEs from sparse data with graph neural networks
Valerii Iakovlev, Markus Heinonen, Harri Lähdesmäki
Poster
Thu 1:00 Sparse Quantized Spectral Clustering
Zhenyu Liao, Romain Couillet, Michael W Mahoney
Poster
Thu 1:00 Counterfactual Generative Networks
Axel Sauer, Andreas Geiger
Poster
Thu 1:00 AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights
Byeongho Heo, Sanghyuk Chun, Seong Joon Oh, Dongyoon Han, Sangdoo Yun, Gyuwan Kim, Youngjung Uh, Jung-Woo Ha
Poster
Thu 1:00 An Unsupervised Deep Learning Approach for Real-World Image Denoising
Dihan Zheng, Sia Huat Tan, Xiaowen Zhang, Zuoqiang Shi, Kaisheng Ma, Chenglong Bao
Poster
Thu 1:00 Retrieval-Augmented Generation for Code Summarization via Hybrid GNN
Shangqing Liu, Yu Chen, Xiaofei Xie, Siow Jing Kai, Yang Liu
Poster
Thu 1:00 Practical Massively Parallel Monte-Carlo Tree Search Applied to Molecular Design
Xiufeng Yang, Tanuj Aasawat, Kazuki Yoshizoe
Poster
Thu 1:00 Go with the flow: Adaptive control for Neural ODEs
Mathieu Chalvidal, Matthew Ricci, Rufin VanRullen, Thomas Serre
Poster
Thu 1:00 Collective Robustness Certificates: Exploiting Interdependence in Graph Neural Networks
Jan Schuchardt, Aleksandar Bojchevski, Johannes Klicpera, Stephan Günnemann
Poster
Thu 1:00 Network Pruning That Matters: A Case Study on Retraining Variants
Duong Le, Binh-Son Hua
Poster
Thu 1:00 ChipNet: Budget-Aware Pruning with Heaviside Continuous Approximations
Rishabh Tiwari, Udbhav Bamba, Arnav Chavan, Deepak Gupta
Poster
Thu 1:00 Distilling Knowledge from Reader to Retriever for Question Answering
Gautier Izacard, Edouard Grave
Poster
Thu 1:00 Optimal Rates for Averaged Stochastic Gradient Descent under Neural Tangent Kernel Regime
Atsushi Nitanda, Taiji Suzuki
Poster
Thu 1:00 GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding
Dmitry Lepikhin, HyoukJoong Lee, Yuanzhong Xu, Dehao Chen, Orhan Firat, Yanping Huang, Maxim Krikun, Noam Shazeer, Zhifeng Chen
Poster
Thu 1:00 Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networks
Shikuang Deng, Shi Gu
Spotlight
Thu 3:15 Winning the L2RPN Challenge: Power Grid Management via Semi-Markov Afterstate Actor-Critic
Deunsol Yoon, Sunghoon Hong, Byung-Jun Lee, Kee-Eung Kim
Spotlight
Thu 5:05 Retrieval-Augmented Generation for Code Summarization via Hybrid GNN
Shangqing Liu, Yu Chen, Xiaofei Xie, Siow Jing Kai, Yang Liu
Spotlight
Thu 5:15 Practical Real Time Recurrent Learning with a Sparse Approximation
Jacob Menick, Erich Elsen, Utku Evci, Simon Osindero, Karen Simonyan, Alex Graves
Poster
Thu 9:00 Dataset Meta-Learning from Kernel Ridge-Regression
Timothy Nguyen, Zhourong Chen, Jaehoon Lee
Poster
Thu 9:00 Deep Networks and the Multiple Manifold Problem
Sam Buchanan, Dar Gilboa, John Wright
Poster
Thu 9:00 Graph Coarsening with Neural Networks
Chen Cai, Dingkang Wang, Yusu Wang
Poster
Thu 9:00 A Critique of Self-Expressive Deep Subspace Clustering
Ben Haeffele, Chong You, Rene Vidal
Poster
Thu 9:00 Neural Spatio-Temporal Point Processes
Ricky T. Q. Chen, Brandon Amos, Maximilian Nickel
Poster
Thu 9:00 Dataset Condensation with Gradient Matching
Bo ZHAO, Konda Reddy Mopuri, Hakan Bilen
Poster
Thu 9:00 Enforcing robust control guarantees within neural network policies
Priya Donti, Melrose Roderick, Mahyar Fazlyab, Zico Kolter
Poster
Thu 9:00 VCNet and Functional Targeted Regularization For Learning Causal Effects of Continuous Treatments
Lizhen Nie, Mao Ye, Qiang Liu, Dan Nicolae
Poster
Thu 9:00 Multi-Class Uncertainty Calibration via Mutual Information Maximization-based Binning
Kanil Patel, William H Beluch, Bin Yang, Michael Pfeiffer, Dan Zhang
Poster
Thu 9:00 Uncertainty in Gradient Boosting via Ensembles
Andrey Malinin, Liudmila Prokhorenkova, Aleksei Ustimenko
Poster
Thu 9:00 Adversarially-Trained Deep Nets Transfer Better: Illustration on Image Classification
Francisco Utrera, Evan Kravitz, N. Benjamin Erichson, Rajiv Khanna, Michael W Mahoney
Poster
Thu 9:00 Learning to live with Dale's principle: ANNs with separate excitatory and inhibitory units
Jonathan Cornford, Damjan Kalajdzievski, Marco Leite, Amélie Lamarquette, Dimitri Kullmann, Blake A Richards
Poster
Thu 9:00 Differentially Private Learning Needs Better Features (or Much More Data)
Florian Tramer, Dan Boneh
Poster
Thu 9:00 BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantization
Huanrui Yang, Lin Duan, Yiran Chen, Hai Li
Poster
Thu 9:00 Meta-Learning of Structured Task Distributions in Humans and Machines
Sreejan Kumar, Ishita Dasgupta, Jonathan Cohen, Nathaniel Daw, Thomas L Griffiths
Poster
Thu 9:00 EigenGame: PCA as a Nash Equilibrium
Ian Gemp, Brian McWilliams, Claire Vernade, Thore Graepel
Poster
Thu 9:00 Implicit Gradient Regularization
David Barrett, Benoit Dherin
Poster
Thu 9:00 Adversarial score matching and improved sampling for image generation
Alexia Jolicoeur-Martineau, Rémi Piché-Taillefer, Ioannis Mitliagkas, Remi Combes
Poster
Thu 9:00 Analyzing the Expressive Power of Graph Neural Networks in a Spectral Perspective
Muhammet Balcilar, Guillaume Renton, Pierre Héroux, Benoit Gaüzère, Sébastien Adam, Paul Honeine
Poster
Thu 9:00 Directed Acyclic Graph Neural Networks
Veronika Thost, Jie Chen
Poster
Thu 9:00 Deconstructing the Regularization of BatchNorm
Yann Dauphin, Ekin Cubuk
Oral
Thu 11:00 VCNet and Functional Targeted Regularization For Learning Causal Effects of Continuous Treatments
Lizhen Nie, Mao Ye, Qiang Liu, Dan Nicolae
Oral
Thu 11:45 Why Are Convolutional Nets More Sample-Efficient than Fully-Connected Nets?
Zhiyuan Li, Yi Zhang, Sanjeev Arora
Spotlight
Thu 13:30 A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference
Sanghyun Hong, Yigitcan Kaya, Ionut-Vlad Modoranu, Tudor Dumitras
Spotlight
Thu 13:40 BUSTLE: Bottom-Up Program Synthesis Through Learning-Guided Exploration
Augustus Odena, Kensen Shi, David Bieber, Rishabh Singh, Charles Sutton, Hanjun Dai
Expo Talk Panel
Thu 14:00 AI Model Efficiency Toolkit talk & demo
Abhi Khobare
Poster
Thu 17:00 Fast Geometric Projections for Local Robustness Certification
Aymeric Fromherz, Klas Leino, Matt Fredrikson, Bryan Parno, Corina Pasareanu
Poster
Thu 17:00 Combining Ensembles and Data Augmentation Can Harm Your Calibration
Yeming Wen, Ghassen Jerfel, Rafael Müller, Michael W Dusenberry, Jasper Snoek, Balaji Lakshminarayanan, Dustin Tran
Poster
Thu 17:00 Combining Label Propagation and Simple Models out-performs Graph Neural Networks
Qian Huang, Horace He, Abhay Singh, Ser-Nam Lim, Austin Benson
Poster
Thu 17:00 HW-NAS-Bench: Hardware-Aware Neural Architecture Search Benchmark
Chaojian Li, Zhongzhi Yu, Yonggan Fu, Yongan Zhang, Yang Zhao, Haoran You, Qixuan Yu, Yue Wang, Cong Hao, Yingyan Lin
Poster
Thu 17:00 Representing Partial Programs with Blended Abstract Semantics
Maxwell Nye, Yewen Pu, Matthew Bowers, Jacob Andreas, Joshua B Tenenbaum, Armando Solar-Lezama
Poster
Thu 17:00 Nonseparable Symplectic Neural Networks
Shiying Xiong, Yunjin Tong, Xingzhe He, Shuqi Yang, Cheng Yang, Bo Zhu
Poster
Thu 17:00 Multi-timescale Representation Learning in LSTM Language Models
Shivangi Mahto, Vy Vo, Javier Turek, Alexander Huth
Poster
Thu 17:00 Neural representation and generation for RNA secondary structures
Zichao Yan, Will Hamilton, Mathieu Blanchette
Poster
Thu 17:00 BiPointNet: Binary Neural Network for Point Clouds
Haotong Qin, Zhongang Cai, Mingyuan Zhang, Yifu Ding, Haiyu Zhao, Shuai Yi, Xianglong Liu, Hao Su
Poster
Thu 17:00 Multi-Prize Lottery Ticket Hypothesis: Finding Accurate Binary Neural Networks by Pruning A Randomly Weighted Network
James Diffenderfer, Bhavya Kailkhura
Poster
Thu 17:00 Convex Regularization behind Neural Reconstruction
Arda Sahiner, Morteza Mardani, Batu Ozturkler, Mert Pilanci, John M Pauly
Poster
Thu 17:00 ARMOURED: Adversarially Robust MOdels using Unlabeled data by REgularizing Diversity
Kangkang Lu, Alfred Nguyen, Xun Xu, Kiran Chari, Yu Jing Goh, CS Foo
Poster
Thu 17:00 Fast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete Verifiers
Kaidi Xu, Huan Zhang, Shiqi Wang, Yihan Wang, Suman Jana, Xue Lin, Cho-Jui Hsieh
Poster
Thu 17:00 MARS: Markov Molecular Sampling for Multi-objective Drug Discovery
Yutong Xie, Chence Shi, Hao Zhou, Yuwei Yang, Weinan Zhang Zhang, Yong Yu, Lei Li
Poster
Thu 17:00 On the Curse of Memory in Recurrent Neural Networks: Approximation and Optimization Analysis
Zhong Li, Jiequn Han, Weinan E, Qianxiao Li
Poster
Thu 17:00 Randomized Automatic Differentiation
Deniz Oktay, Nick McGreivy, Joshua Aduol, Alex Beatson, Ryan P Adams
Poster
Thu 17:00 How Much Over-parameterization Is Sufficient to Learn Deep ReLU Networks?
Zixiang Chen, Yuan Cao, Difan Zou, Quanquan Gu
Poster
Thu 17:00 The Recurrent Neural Tangent Kernel
Sina Alemohammad, Jack Wang, Randall Balestriero, Richard Baraniuk
Poster
Thu 17:00 CPT: Efficient Deep Neural Network Training via Cyclic Precision
Yonggan Fu, Han Guo, Meng Li, Xin Yang, Yining Ding, Vikas Chandra, Yingyan Lin
Poster
Thu 17:00 Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data
Colin Wei, Kendrick Shen, Yining Chen, Tengyu Ma
Poster
Thu 17:00 Few-Shot Learning via Learning the Representation, Provably
Simon Du, Wei Hu, Sham M Kakade, Jason Lee, Qi Lei
Poster
Thu 17:00 Neural Pruning via Growing Regularization
Huan Wang, Can Qin, Yulun Zhang, Yun Fu
Poster
Thu 17:00 Calibration of Neural Networks using Splines
Kartik Gupta, Amir Rahimi, Thalaiyasingam Ajanthan, Thomas Mensink, Cristian Sminchisescu, Richard Hartley
Poster
Thu 17:00 Minimum Width for Universal Approximation
Sejun Park, Chulhee (Charlie) Yun, Jaeho Lee, Jinwoo Shin
Poster
Thu 17:00 FedBN: Federated Learning on Non-IID Features via Local Batch Normalization
Xiaoxiao Li, Meirui Jiang, Xiaofei Zhang, Michael Kamp, Qi Dou
Poster
Thu 17:00 Clustering-friendly Representation Learning via Instance Discrimination and Feature Decorrelation
Yaling Tao, Kentaro Takagi, Kouta Nakata
Poster
Thu 17:00 DynaTune: Dynamic Tensor Program Optimization in Deep Neural Network Compilation
Minjia Zhang, Menghao Li, Chi Wang, Mingqin Li
Poster
Thu 17:00 Neural Thompson Sampling
Weitong ZHANG, Dongruo Zhou, Lihong Li, Quanquan Gu
Poster
Thu 17:00 Learning Energy-Based Generative Models via Coarse-to-Fine Expanding and Sampling
Yang Zhao, Jianwen Xie, Ping Li
Poster
Thu 17:00 Global Convergence of Three-layer Neural Networks in the Mean Field Regime
Huy Tuan Pham, Phan-Minh Nguyen
Oral
Thu 19:00 Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data
Colin Wei, Kendrick Shen, Yining Chen, Tengyu Ma
Spotlight
Thu 20:35 Sparse Quantized Spectral Clustering
Zhenyu Liao, Romain Couillet, Michael W Mahoney
Spotlight
Thu 21:18 MARS: Markov Molecular Sampling for Multi-objective Drug Discovery
Yutong Xie, Chence Shi, Hao Zhou, Yuwei Yang, Weinan Zhang Zhang, Yong Yu, Lei Li
Workshop
Fri 5:50 Energy-Based Models: Current Perspectives, Challenges, and Opportunities
Marc Dymetman, Adji Bousso Dieng, Hady Elsahar, Igor Mordatch, Marc'Aurelio Ranzato
Workshop
Fri 6:00 Keynote 3: Ehsan Saboori. Title: Deep learning model compression using neural network design space exploration
Workshop
Fri 6:14 Density Approximation in Deep Generative Models with Kernel Transfer Operators
Zhichun Huang
Workshop
Fri 6:22 On Adversarial Robustness: A Neural Architecture Search perspective
Chaitanya Devaguptapu
Workshop
Fri 6:30 Break & Poster session 1
Workshop
Fri 6:30 How Can Findings About The Brain Improve AI Systems?
Shinji Nishimoto, Leila Wehbe, Alexander Huth, Javier Turek, Nicole Beckage, Vy Vo, Mariya Toneva, Hsiang-Yun Chien, Shailee Jain, Richard Antonello
Workshop
Fri 6:34 Min-Entropy Sampling Might Lead to Better Generalization in Deep Text Classification, Nimrah Shakeel
Nimrah Shakeel
Workshop
Fri 6:45 Investigating Ground-level Ozone Formation: A Case Study in Taiwan
Yu-Wen Chen, Sourav Medya, Yi-Chun Chen
Workshop
Fri 7:00 Generalization beyond the training distribution in brains and machines
Christina Funke, Judith Borowski, Drew Linsley, Xavier Boix
Workshop
Fri 7:00 Workshop on Weakly Supervised Learning
Benjamin Roth, Barbara Plank, Alex Ratner, Katharina Kann, Dietrich Klakow, Michael Hedderich
Workshop
Fri 7:05 Model Discovery in the Sparse Sampling Regime
Gert-Jan Both, Georges Tod, Remy Kusters
Workshop
Fri 7:10 Poster Spotlight "Measuring Uncertainty through Bayesian Learning of Deep Neural Network Structure"
Zhijie Deng
Workshop
Fri 7:45 Coffee break and short paper presentations and discussion.
Hernán Lira, Björn Lütjens, Mark Veillette, Dava Newman, Konstantin Klemmer, Sudipan Saha, Matthias Kahl, Lin Xu, Xiaoxiang Zhu, Hiske Overweg, Ioannis N. Athanasiadis, Nayat Sánchez-Pi, Luis Martí
Workshop
Fri 8:29 Detection of COVID-19 Disease using Deep Neural Networks with Ultrasound Imaging
Dennis Hernando Núñez Fernández
Workshop
Fri 8:57 Data-driven Weight Initialization with Sylvester Solvers
Buna Das
Workshop
Fri 9:05 Assessing Physics Informed Neural Networks in Ocean Modelling and Climate Change Applications
Taco de Wolff, Hugo Carrillo Lincopi, Luis Martí, Nayat Sánchez-Pi
Workshop
Fri 9:25 Deep Embedded Clustering for BioAcoustic Clustering of Marine Mammal Vocalization
Ali Jahangirnezhad, Afra Mashhadi
Workshop
Fri 9:30 Break & Poster session 2
Workshop
Fri 10:30 Gal Mishne: Visualizing the PHATE of deep neural networks
Gal Mishne
Workshop
Fri 10:54 TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryption
Ayoub Benaissa
Workshop
Fri 11:35 Spotlight 7: Emilien Dupont, COIN: COmpression with Implicit Neural representations
Workshop
Fri 11:40 Spotlight 8: Yunhao Ge, Graph Autoencoder for Graph Compression and Representation Learning
Workshop
Fri 11:40 Deep Kernels with Probabilistic Embeddings for Small-Data Learning
Ankur Mallick
Workshop
Fri 11:51 "Generative Modeling for Music Generation" by Sander Dieleman, DeepMind
Sander Dieleman
Workshop
Fri 14:02 Invited Talk: A deep learning theory for neural networks grounded in physics
Benjamin Scellier
Workshop
Fri 14:50 Don't Stack Layers in Graph Neural Networks, Wire Them Randomly
Diego Valsesia, Giulia Fracastoro, Enrico Magli
Workshop
Talk Less, Smile More: Reducing Communication with Distributed Auto-Differentiation
Bradley Baker, Vince Calhoun, Barak Pearlmutter, Sergey Plis
Workshop
PyVertical: A Vertical Federated Learning Framework for Multi-headed SplitNN
Daniele Romanini, Adam Hall, Pavlos Papadopoulos, Tom Titcombe, Abbas Ismail, Tudor Cebere, Robert Sandmann, Robin Roehm, Michael Hoeh
Workshop
FedGraphNN: A Federated Learning System and Benchmark for Graph Neural Networks
Chaoyang He, Keshav Balasubramanian, Emir Ceyani, Yu Rong, Junzhou Huang, Murali Annavaram, Salman Avestimehr
Workshop
Direct Federated Neural Architecture Search
Anubhav Garg, Amit Saha, Debojyoti Dutta
Workshop
A Graphical Model Perspective on Federated Learning
Christos Louizos, Matthias Reisser, Joseph Soriaga, Max Welling
Workshop
Syft: A Platform for Universally Deployable Structured Transparency
Adam Hall
Workshop
SWIFT: Super-fast and Robust Privacy-Preserving Machine Learning
Nishat Koti, Mahak Pancholi, Arpita Patra, Ajith Suresh
Workshop
TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryption
Ayoub Benaissa
Workshop
Speeding Up Neural Network Verification via Automated Algorithm Configuration
Matthias König
Workshop
GateNet: Bridging the gap between Binarized Neural Network and FHE evaluation
Cheng Fu
Workshop
Non-Singular Adversarial Robustness of Neural Networks
Chia-Yi Hsu, Pin-Yu Chen
Workshop
Baseline Pruning-Based Approach to Trojan Detection in Neural Networks
Peter Bajcsy
Workshop
Practical Defences Against Model Inversion Attacks for Split Neural Networks
Tom Titcombe, Adam Hall, Pavlos Papadopoulos, Daniele Romanini
Workshop
Membership Inference Attack on Graph Neural Networks
Iyiola Emmanuel Olatunji, Wolfgang Nejdl, Megha Khosla
Workshop
MPCLeague: Robust 4-party Computation for Privacy-Preserving Machine Learning
Nishat Koti, Arpita Patra, Ajith Suresh
Workshop
Layer-wise Characterization of Latent Information Leakage in Federated Learning
Fan Mo, Anastasia Borovykh, Mohammad Malekzadeh, Hamed Haddadi, Soteris Demetriou
Workshop
High-Robustness, Low-Transferability Fingerprinting of Neural Networks
Siyue Wang
Workshop
Subnet Replacement: Deployment-stage backdoor attack against deep neural networks in gray-box setting
Xiangyu QI
Workshop
Sparse Coding Frontend for Robust Neural Networks
Can Bakiskan
Workshop
What is Going on Inside Recurrent Meta Reinforcement Learning Agents?
Safa Alver, Doina Precup
Workshop
Self-Constructing Neural Networks through Random Mutation
Samuel Schmidgall
Workshop
UNDERSTANDING CLIPPED FEDAVG: CONVERGENCE AND CLIENT-LEVEL DIFFERENTIAL PRIVACY
Xinwei Zhang, Xiangyi Chen, Jinfeng Yi, Steven Wu, Mingyi Hong
Workshop
COMBO: Conservative Offline Model-Based Policy Optimization
Tianhe (Kevin) Yu, Aviral Kumar, Aravind Rajeswaran, Rafael Rafailov, Sergey Levine, Chelsea Finn