Workshop

DEEP GRADIENT ATTACK WITH STRONG DP-SGD LOWER BOUND FOR LABEL PRIVACY
Sen Yuan

Poster

Mon 9:00

Multi-Level Local SGD: Distributed SGD for Heterogeneous Hierarchical Networks
Timothy Castiglia · Anirban Das · Stacy Patterson

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 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 1:00

Distributed Momentum for Byzantine-resilient Stochastic Gradient Descent
El Mahdi El Mhamdi · Rachid Guerraoui · Sébastien Rouault

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

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 17:00

Bypassing the Ambient Dimension: Private SGD with Gradient Subspace Identification
Yingxue Zhou · Steven Wu · Arindam Banerjee

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