Filter by Keyword:

71 Results

Poster
Mon 1:00 SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization
A F M Shahab Uddin, Mst. Sirazam Monira, Wheemyung Shin, TaeChoong Chung, Sung-Ho Bae
Poster
Mon 1:00 MELR: Meta-Learning via Modeling Episode-Level Relationships for Few-Shot Learning
Nanyi Fei, Zhiwu Lu, Tao Xiang, Songfang Huang
Poster
Mon 1:00 Batch Reinforcement Learning Through Continuation Method
Yijie Guo, Shengyu Feng, Nicolas Le Roux, Ed H. Chi, Honglak Lee, Minmin Chen
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 1:00 Wasserstein-2 Generative Networks
Alexander Korotin, Vage Egiazarian, Arip Asadulaev, Alexander Safin, Evgeny Burnaev
Poster
Mon 1:00 Towards Robustness Against Natural Language Word Substitutions
Xinshuai Dong, Anh Tuan Luu, Rongrong Ji, Hong Liu
Poster
Mon 9:00 Graph Convolution with Low-rank Learnable Local Filters
Xiuyuan Cheng, Zichen Miao, Qiang Qiu
Poster
Mon 9:00 Shapley Explanation Networks
Rui Wang, Xiaoqian Wang, David Inouye
Oral
Mon 11:00 Federated Learning Based on Dynamic Regularization
Durmus Alp Emre Acar, Yue Zhao, Ramon Matas, Matthew Mattina, Paul Whatmough, Venkatesh Saligrama
Spotlight
Mon 12:25 Sharpness-aware Minimization for Efficiently Improving Generalization
Pierre Foret, Ariel Kleiner, Hossein Mobahi, Behnam Neyshabur
Poster
Mon 17:00 Optimal Regularization can Mitigate Double Descent
Preetum Nakkiran, Prayaag Venkat, Sham M Kakade, Tengyu Ma
Poster
Mon 17:00 PseudoSeg: Designing Pseudo Labels for Semantic Segmentation
Yuliang Zou, Zizhao Zhang, Han Zhang, Chun-Liang Li, Xiao Bian, Jia-Bin Huang, Tomas Pfister
Poster
Mon 17:00 Remembering for the Right Reasons: Explanations Reduce Catastrophic Forgetting
Sayna Ebrahimi, Suzanne Petryk, Akash Gokul, William Gan, Joseph E Gonzalez, Marcus Rohrbach, trevor darrell
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 Regularization Matters in Policy Optimization - An Empirical Study on Continuous Control
Zhuang Liu, Xuanlin Li, Bingyi Kang, trevor darrell
Poster
Mon 17:00 On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning
Ren Wang, Kaidi Xu, Sijia Liu, Pin-Yu Chen, Lily Weng, Chuang Gan, Meng Wang
Spotlight
Mon 21:36 Graph Convolution with Low-rank Learnable Local Filters
Xiuyuan Cheng, Zichen Miao, Qiang Qiu
Poster
Tue 1:00 Intraclass clustering: an implicit learning ability that regularizes DNNs
Simon Carbonnelle, Christophe De Vleeschouwer
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
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
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 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 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 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 On the Origin of Implicit Regularization in Stochastic Gradient Descent
Samuel Smith, Benoit Dherin, David Barrett, Soham De
Spotlight
Tue 11:30 How Does Mixup Help With Robustness and Generalization?
Linjun Zhang, Zhun Deng, Kenji Kawaguchi, Amirata Ghorbani, James Zou
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 Fuzzy Tiling Activations: A Simple Approach to Learning Sparse Representations Online
Yangchen Pan, Kirby Banman, Martha White
Poster
Tue 17:00 Monotonic Kronecker-Factored Lattice
William Bakst, Nobuyuki Morioka, Erez Louidor
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 CoDA: Contrast-enhanced and Diversity-promoting Data Augmentation for Natural Language Understanding
Yanru Qu, Dinghan Shen, Yelong Shen, Sandra Sajeev, Weizhu Chen, Jiawei Han
Poster
Tue 17:00 Generalized Variational Continual Learning
Noel Loo, Siddharth Swaroop, Rich E Turner
Poster
Tue 17:00 Fantastic Four: Differentiable and Efficient Bounds on Singular Values of Convolution Layers
ssingla Singla, Soheil Feizi
Poster
Tue 17:00 A unifying view on implicit bias in training linear neural networks
Chulhee (Charlie) Yun, Shankar Krishnan, Hossein Mobahi
Spotlight
Tue 20:20 Async-RED: A Provably Convergent Asynchronous Block Parallel Stochastic Method using Deep Denoising Priors
Yu Sun, Jiaming Liu, Yiran Sun, Brendt Wohlberg, Ulugbek Kamilov
Poster
Wed 1:00 FOCAL: Efficient Fully-Offline Meta-Reinforcement Learning via Distance Metric Learning and Behavior Regularization
Lanqing Li, Rui Yang, Dijun Luo
Poster
Wed 1:00 On Data-Augmentation and Consistency-Based Semi-Supervised Learning
Atin Ghosh, alexandre thiery
Poster
Wed 1:00 Improving Relational Regularized Autoencoders with Spherical Sliced Fused Gromov Wasserstein
Khai Nguyen, Son Nguyen, Nhat Ho, Tung Pham, Hung Bui
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 How Does Mixup Help With Robustness and Generalization?
Linjun Zhang, Zhun Deng, Kenji Kawaguchi, Amirata Ghorbani, James Zou
Poster
Wed 9:00 Continuous Wasserstein-2 Barycenter Estimation without Minimax Optimization
Alexander Korotin, Lingxiao Li, Justin Solomon, Evgeny Burnaev
Poster
Wed 9:00 Neural Networks for Learning Counterfactual G-Invariances from Single Environments
S Chandra Mouli, Bruno Ribeiro
Poster
Wed 9:00 Sharpness-aware Minimization for Efficiently Improving Generalization
Pierre Foret, Ariel Kleiner, Hossein Mobahi, Behnam Neyshabur
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 Influence Functions in Deep Learning Are Fragile
Samyadeep Basu, Phil Pope, Soheil Feizi
Poster
Wed 17:00 Local Convergence Analysis of Gradient Descent Ascent with Finite Timescale Separation
Tanner Fiez, Lillian J Ratliff
Spotlight
Wed 20:30 Towards Robustness Against Natural Language Word Substitutions
Xinshuai Dong, Anh Tuan Luu, Rongrong Ji, Hong Liu
Spotlight
Wed 21:25 Regularization Matters in Policy Optimization - An Empirical Study on Continuous Control
Zhuang Liu, Xuanlin Li, Bingyi Kang, trevor darrell
Poster
Thu 1:00 Incremental few-shot learning via vector quantization in deep embedded space
Kuilin Chen, Chi-Guhn Lee
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 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 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 Rethinking Soft Labels for Knowledge Distillation: A Bias–Variance Tradeoff Perspective
Helong Zhou, Liangchen Song, Jiajie Chen, Ye Zhou, Guoli Wang, Junsong Yuan, Qian Zhang
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
Poster
Thu 17:00 In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning
Mamshad Nayeem Rizve, Kevin Duarte, Yogesh S Rawat, Mubarak Shah
Poster
Thu 17:00 Extreme Memorization via Scale of Initialization
Harsh Mehta, Ashok Cutkosky, Behnam Neyshabur
Poster
Thu 17:00 Async-RED: A Provably Convergent Asynchronous Block Parallel Stochastic Method using Deep Denoising Priors
Yu Sun, Jiaming Liu, Yiran Sun, Brendt Wohlberg, Ulugbek Kamilov
Poster
Thu 17:00 Learning to Make Decisions via Submodular Regularization
Ayya Alieva, Aiden Aceves, Jialin Song, Stephen Mayo, Yisong Yue, Yuxin Chen
Poster
Thu 17:00 Neural Pruning via Growing Regularization
Huan Wang, Can Qin, Yulun Zhang, Yun Fu
Poster
Thu 17:00 CO2: Consistent Contrast for Unsupervised Visual Representation Learning
Chen Wei, Huiyu Wang, Wei Shen, Alan Yuille
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 $i$-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning
Kibok Lee, Yian Zhu, Kihyuk Sohn, Chun-Liang Li, Jinwoo Shin, Honglak Lee
Poster
Thu 17:00 Heteroskedastic and Imbalanced Deep Learning with Adaptive Regularization
Kaidi Cao, Yining Chen, Junwei Lu, Nikos Arechiga, Adrien Gaidon, Tengyu Ma
Poster
Thu 17:00 Convex Regularization behind Neural Reconstruction
Arda Sahiner, Morteza Mardani, Batu Ozturkler, Mert Pilanci, John M Pauly
Poster
Thu 17:00 No MCMC for me: Amortized sampling for fast and stable training of energy-based models
Will Grathwohl, Jacob Kelly, Milad Hashemi, Mohammad Norouzi, Kevin Swersky, David Duvenaud
Poster
Thu 17:00 Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data
Colin Wei, Kendrick Shen, Yining Chen, Tengyu Ma
Oral
Thu 19:00 Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data
Colin Wei, Kendrick Shen, Yining Chen, Tengyu Ma
Workshop
Regularization Can Help Mitigate Poisoning Attacks... with the Right Hyperparameters
Javier Carnerero-Cano