|
Poster
|
Tue 2:30
|
How Sharpness-Aware Minimization Minimizes Sharpness?
Kaiyue Wen · Tengyu Ma · Zhiyuan Li
|
|
|
Poster
|
Mon 7:30
|
Implicit Bias of Large Depth Networks: a Notion of Rank for Nonlinear Functions
Arthur Jacot
|
|
|
Oral
|
Mon 6:10
|
Implicit Bias of Large Depth Networks: a Notion of Rank for Nonlinear Functions
Arthur Jacot
|
|
|
Poster
|
Mon 2:30
|
Why (and When) does Local SGD Generalize Better than SGD?
Xinran Gu · Kaifeng Lyu · Longbo Huang · Sanjeev Arora
|
|
|
Poster
|
Mon 7:30
|
Benign Overfitting in Classification: Provably Counter Label Noise with Larger Models
Kaiyue Wen · Jiaye Teng · Jingzhao Zhang
|
|
|
Poster
|
|
On Accelerated Perceptrons and Beyond
Guanghui Wang · Rafael Hanashiro · Etash Guha · Jacob Abernethy
|
|
|
Poster
|
Tue 7:30
|
The Implicit Bias of Minima Stability in Multivariate Shallow ReLU Networks
Mor Shpigel Nacson · Rotem Mulayoff · Greg Ongie · Tomer Michaeli · Daniel Soudry
|
|
|
Poster
|
Mon 2:30
|
A new characterization of the edge of stability based on a sharpness measure aware of batch gradient distribution
Sungyoon Lee · Cheongjae Jang
|
|
|
Poster
|
Wed 2:30
|
Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability
Alex Damian · Eshaan Nichani · Jason Lee
|
|
|
Oral
|
Tue 1:50
|
The Asymmetric Maximum Margin Bias of Quasi-Homogeneous Neural Networks
Daniel Kunin · Atsushi Yamamura · Chao Ma · Surya Ganguli
|
|
|
Poster
|
Tue 2:30
|
The Asymmetric Maximum Margin Bias of Quasi-Homogeneous Neural Networks
Daniel Kunin · Atsushi Yamamura · Chao Ma · Surya Ganguli
|
|
|
Poster
|
|
Understanding Why Generalized Reweighting Does Not Improve Over ERM
Runtian Zhai · Chen Dan · Zico Kolter · Pradeep K Ravikumar
|
|
