Filter by Keyword:

32 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
Spotlight
Mon 4:40 How Benign is Benign Overfitting ?
Amartya Sanyal, Puneet Dokania, Varun Kanade, Philip Torr
Poster
Mon 9:00 Multi-Level Local SGD: Distributed SGD for Heterogeneous Hierarchical Networks
Timothy Castiglia, Anirban Das, Stacy Patterson
Poster
Mon 9:00 Fast convergence of stochastic subgradient method under interpolation
Huang Fang, Zhenan Fan, Michael Friedlander
Spotlight
Mon 12:35 Systematic generalisation with group invariant predictions
Faruk Ahmed, Yoshua Bengio, Harm van Seijen, Aaron Courville
Poster
Mon 17:00 Bypassing the Ambient Dimension: Private SGD with Gradient Subspace Identification
Yingxue Zhou, Steven Wu, Arindam Banerjee
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
Poster
Tue 1:00 Distributed Momentum for Byzantine-resilient Stochastic Gradient Descent
El Mahdi El Mhamdi, Rachid Guerraoui, Sébastien Rouault
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 Systematic generalisation with group invariant predictions
Faruk Ahmed, Yoshua Bengio, Harm van Seijen, Aaron Courville
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 How Benign is Benign Overfitting ?
Amartya Sanyal, Puneet Dokania, Varun Kanade, Philip Torr
Poster
Tue 9:00 On the Origin of Implicit Regularization in Stochastic Gradient Descent
Samuel Smith, Benoit Dherin, David Barrett, Soham De
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 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 Why Are Convolutional Nets More Sample-Efficient than Fully-Connected Nets?
Zhiyuan Li, Yi Zhang, Sanjeev Arora
Poster
Wed 1:00 Byzantine-Resilient Non-Convex Stochastic Gradient Descent
Zeyuan Allen-Zhu, Faeze Ebrahimianghazani, Jerry Li, Dan Alistarh
Poster
Wed 1:00 A Better Alternative to Error Feedback for Communication-Efficient Distributed Learning
Samuel Horváth, Peter Richtarik
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 New Bounds For Distributed Mean Estimation and Variance Reduction
Peter Davies, Vijaykrishna Gurunathan, Niusha Moshrefi, Saleh Ashkboos, Dan Alistarh
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
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 1:00 Repurposing Pretrained Models for Robust Out-of-domain Few-Shot Learning
Namyeong Kwon, Hwidong Na, Gabriel Huang, Simon Lacoste-Julien
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
Oral
Thu 11:45 Why Are Convolutional Nets More Sample-Efficient than Fully-Connected Nets?
Zhiyuan Li, Yi Zhang, Sanjeev Arora
Poster
Thu 17:00 Extreme Memorization via Scale of Initialization
Harsh Mehta, Ashok Cutkosky, Behnam Neyshabur
Workshop
Fri 10:42 Privacy Amplification via Iteration for Shuffled and Online PNSGD
Matteo Sordello, Zhiqi Bu, Jinshuo Dong, Weijie J Su
Workshop
Fri 12:15 A Better Bound Gives a Hundred Rounds: Enhanced Privacy Guarantees via f-Divergences
Lalitha Sankar
Workshop
Personalized Federated Learning: A Unified Framework and Universal Optimization Techniques
Filip Hanzely, Boxin Zhao, Mladen Kolar
Workshop
Privacy Amplification via Iteration for Shuffled and Online PNSGD
Matteo Sordello, Zhiqi Bu, Jinshuo Dong, Weijie J Su
Workshop
DEEP GRADIENT ATTACK WITH STRONG DP-SGD LOWER BOUND FOR LABEL PRIVACY
Sen Yuan
Workshop
UNDERSTANDING CLIPPED FEDAVG: CONVERGENCE AND CLIENT-LEVEL DIFFERENTIAL PRIVACY
Xinwei Zhang, Xiangyi Chen, Jinfeng Yi, Steven Wu, Mingyi Hong