|
Workshop
|
|
Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability
Alex Damian · Eshaan Nichani · Jason Lee
|
|
|
Poster
|
Tue 14:00
|
Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction
Kaifeng Lyu · Zhiyuan Li · Sanjeev Arora
|
|
|
Poster
|
Tue 9:00
|
Differentially Private Learning Needs Hidden State (Or Much Faster Convergence)
Jiayuan Ye · Reza Shokri
|
|
|
Poster
|
|
Analyzing Sharpness along GD Trajectory: Progressive Sharpening and Edge of Stability
Zixuan Wang · Zhouzi Li · Jian Li
|
|
|
Poster
|
Wed 14:00
|
Gradient Descent: The Ultimate Optimizer
Kartik Chandra · Audrey Xie · Jonathan Ragan-Kelley · ERIK MEIJER
|
|
|
Poster
|
Wed 14:00
|
Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent
Zhiyuan Li · Tianhao Wang · Jason Lee · Sanjeev Arora
|
|
|
Workshop
|
|
Stochastic Gradient Descent-Ascent: Unified Theory and New Efficient Methods
Aleksandr Beznosikov · Eduard Gorbunov · Hugo Berard · Nicolas Loizou
|
|
|
Poster
|
Thu 14:00
|
Statistical Learning and Inverse Problems: A Stochastic Gradient Approach
Yuri Fonseca · Yuri Saporito
|
|
|
Poster
|
Wed 9:00
|
Generalization Bounds for Stochastic Gradient Descent via Localized εε-Covers
Sejun Park · Umut Simsekli · Murat Erdogdu
|
|
|
Poster
|
Tue 9:00
|
Global Convergence and Stability of Stochastic Gradient Descent
Vivak Patel · Shushu Zhang · Bowen Tian
|
|
|
Poster
|
Tue 14:00
|
Trajectory of Mini-Batch Momentum: Batch Size Saturation and Convergence in High Dimensions
Kiwon Lee · Andrew Cheng · Elliot Paquette · Courtney Paquette
|
|
|
Poster
|
Tue 9:00
|
Dynamics of SGD with Stochastic Polyak Stepsizes: Truly Adaptive Variants and Convergence to Exact Solution
Antonio Orvieto · Simon Lacoste-Julien · Nicolas Loizou
|
|
