Filter by Keyword:

64 Results

Poster
Mon 1:00 Noise against noise: stochastic label noise helps combat inherent label noise
Pengfei Chen, Guangyong Chen, Junjie Ye, jingwei zhao, Pheng-Ann Heng
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 Fast convergence of stochastic subgradient method under interpolation
Huang Fang, Zhenan Fan, Michael Friedlander
Poster
Mon 9:00 Gradient Projection Memory for Continual Learning
Gobinda Saha, Isha Garg, Kaushik Roy
Poster
Mon 9:00 Multi-Level Local SGD: Distributed SGD for Heterogeneous Hierarchical Networks
Timothy Castiglia, Anirban Das, Stacy Patterson
Poster
Mon 9:00 On the Impossibility of Global Convergence in Multi-Loss Optimization
Alistair Letcher
Oral
Mon 11:15 Gradient Projection Memory for Continual Learning
Gobinda Saha, Isha Garg, Kaushik Roy
Spotlight
Mon 12:15 On the Theory of Implicit Deep Learning: Global Convergence with Implicit Layers
Kenji Kawaguchi
Spotlight
Mon 12:25 Sharpness-aware Minimization for Efficiently Improving Generalization
Pierre Foret, Ariel Kleiner, Hossein Mobahi, Behnam Neyshabur
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 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 Proximal Gradient Descent-Ascent: Variable Convergence under KŁ Geometry
Ziyi Chen, Yi Zhou, Tengyu Xu, Yingbin Liang
Poster
Mon 17:00 The Role of Momentum Parameters in the Optimal Convergence of Adaptive Polyak's Heavy-ball Methods
Wei Tao, sheng long, Gaowei Wu, Qing Tao
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
Poster
Tue 1:00 Distributed Momentum for Byzantine-resilient Stochastic Gradient Descent
El Mahdi El Mhamdi, Rachid Guerraoui, Sébastien Rouault
Poster
Tue 1:00 Coping with Label Shift via Distributionally Robust Optimisation
Jingzhao Zhang, Aditya Krishna Menon, Andreas Veit, Srinadh Bhojanapalli, Sanjiv Kumar, Suvrit Sra
Poster
Tue 1:00 Computational Separation Between Convolutional and Fully-Connected Networks
Eran Malach, Shai Shalev-Shwartz
Spotlight
Tue 4:48 Noise against noise: stochastic label noise helps combat inherent label noise
Pengfei Chen, Guangyong Chen, Junjie Ye, jingwei zhao, Pheng-Ann Heng
Poster
Tue 9:00 On the Theory of Implicit Deep Learning: Global Convergence with Implicit Layers
Kenji Kawaguchi
Poster
Tue 9:00 On the Origin of Implicit Regularization in Stochastic Gradient Descent
Samuel Smith, Benoit Dherin, David Barrett, Soham De
Poster
Tue 9:00 On the Dynamics of Training Attention Models
Haoye Lu, Yongyi Mao, Amiya Nayak
Poster
Tue 9:00 Direction Matters: On the Implicit Bias of Stochastic Gradient Descent with Moderate Learning Rate
Jingfeng Wu, Difan Zou, vladimir braverman, Quanquan Gu
Poster
Tue 9:00 Towards Resolving the Implicit Bias of Gradient Descent for Matrix Factorization: Greedy Low-Rank Learning
Zhiyuan Li, Yuping Luo, Kaifeng Lyu
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
Oral
Tue 12:00 Randomized Automatic Differentiation
Deniz Oktay, Nick McGreivy, Joshua Aduol, Alex Beatson, Ryan P Adams
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 Understanding the role of importance weighting for deep learning
Da Xu, Yuting Ye, Chuanwei Ruan
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 Deep Equals Shallow for ReLU Networks in Kernel Regimes
Alberto Bietti, Francis Bach
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 Usable Information and Evolution of Optimal Representations During Training
Michael Kleinman, Alessandro Achille, Daksh Idnani, Jonathan Kao
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 How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks
Keyulu Xu, Mozhi Zhang, Jingling Li, Simon Du, Ken-Ichi Kawarabayashi, Stefanie Jegelka
Oral
Tue 19:55 Global Convergence of Three-layer Neural Networks in the Mean Field Regime
Huy Tuan Pham, Phan-Minh Nguyen
Spotlight
Tue 20:30 Individually Fair Gradient Boosting
Alexander Vargo, Fan Zhang, Mikhail Yurochkin, Yuekai Sun
Poster
Wed 1:00 Differentiable Segmentation of Sequences
Erik Scharwächter, Jonathan Lennartz, Emmanuel Müller
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 Learning Associative Inference Using Fast Weight Memory
Imanol Schlag, Tsendsuren Munkhdalai, Jürgen Schmidhuber
Poster
Wed 1:00 Byzantine-Resilient Non-Convex Stochastic Gradient Descent
Zeyuan Allen-Zhu, Faeze Ebrahimianghazani, Jerry Li, Dan Alistarh
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
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 Sliced Kernelized Stein Discrepancy
Wenbo Gong, Yingzhen Li, José Miguel Hernández Lobato
Poster
Wed 9:00 Sharpness-aware Minimization for Efficiently Improving Generalization
Pierre Foret, Ariel Kleiner, Hossein Mobahi, Behnam Neyshabur
Poster
Wed 17:00 Local Convergence Analysis of Gradient Descent Ascent with Finite Timescale Separation
Tanner Fiez, Lillian J Ratliff
Poster
Wed 17:00 Individually Fair Gradient Boosting
Alexander Vargo, Fan Zhang, Mikhail Yurochkin, Yuekai Sun
Spotlight
Wed 20:20 Understanding the role of importance weighting for deep learning
Da Xu, Yuting Ye, Chuanwei Ruan
Oral
Thu 0:30 Optimal Rates for Averaged Stochastic Gradient Descent under Neural Tangent Kernel Regime
Atsushi Nitanda, Taiji Suzuki
Poster
Thu 1:00 Do not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning
Da Yu, Huishuai Zhang, Wei Chen, Tie-Yan Liu
Poster
Thu 1:00 Optimal Rates for Averaged Stochastic Gradient Descent under Neural Tangent Kernel Regime
Atsushi Nitanda, Taiji Suzuki
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 The inductive bias of ReLU networks on orthogonally separable data
Mary Phuong, Christoph H Lampert
Poster
Thu 1:00 A Diffusion Theory For Deep Learning Dynamics: Stochastic Gradient Descent Exponentially Favors Flat Minima
Zeke Xie, Issei Sato, Masashi Sugiyama
Poster
Thu 9:00 Meta-learning with negative learning rates
Alberto Bernacchia
Poster
Thu 9:00 Linear Last-iterate Convergence in Constrained Saddle-point Optimization
Chen-Yu Wei, Chung-Wei Lee, Mengxiao Zhang, Haipeng Luo
Poster
Thu 9:00 Deep Networks and the Multiple Manifold Problem
Sam Buchanan, Dar Gilboa, John Wright
Poster
Thu 9:00 Initialization and Regularization of Factorized Neural Layers
Misha Khodak, Neil Tenenholtz, Lester Mackey, Nicolo Fusi
Poster
Thu 9:00 Implicit Gradient Regularization
David Barrett, Benoit Dherin
Poster
Thu 17:00 Randomized Automatic Differentiation
Deniz Oktay, Nick McGreivy, Joshua Aduol, Alex Beatson, Ryan P Adams
Poster
Thu 17:00 Global Convergence of Three-layer Neural Networks in the Mean Field Regime
Huy Tuan Pham, Phan-Minh Nguyen
Poster
Thu 17:00 How Much Over-parameterization Is Sufficient to Learn Deep ReLU Networks?
Zixiang Chen, Yuan Cao, Difan Zou, Quanquan Gu
Workshop
Fri 10:42 Privacy Amplification via Iteration for Shuffled and Online PNSGD
Matteo Sordello, Zhiqi Bu, Jinshuo Dong, Weijie J Su
Workshop
Fri 11:40 Deep Kernels with Probabilistic Embeddings for Small-Data Learning
Ankur Mallick
Workshop
Fri 12:15 A Better Bound Gives a Hundred Rounds: Enhanced Privacy Guarantees via f-Divergences
Lalitha Sankar
Workshop
Privacy Amplification via Iteration for Shuffled and Online PNSGD
Matteo Sordello, Zhiqi Bu, Jinshuo Dong, Weijie J Su