The Asymmetric Maximum Margin Bias of Quasi-Homogeneous Neural Networks

The Asymmetric Maximum Margin Bias of Quasi-Homogeneous Neural Networks

7 October 2022

Atsushi Yamamura

Chao Ma

Papers citing "The Asymmetric Maximum Margin Bias of Quasi-Homogeneous Neural Networks"

6 / 6 papers shown

Title
The late-stage training dynamics of (stochastic) subgradient descent on homogeneous neural networks Sholom Schechtman Nicolas Schreuder 144 0 0 08 Feb 2025
From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks Clémentine Dominé Nicolas Anguita A. Proca Lukas Braun D. Kunin P. Mediano Andrew M. Saxe 32 3 0 22 Sep 2024
An Unconstrained Layer-Peeled Perspective on Neural Collapse Wenlong Ji Yiping Lu Yiliang Zhang Zhun Deng Weijie J. Su 127 83 0 06 Oct 2021
On Margin Maximization in Linear and ReLU Networks Gal Vardi Ohad Shamir Nathan Srebro 47 28 0 06 Oct 2021
Exploring Deep Neural Networks via Layer-Peeled Model: Minority Collapse in Imbalanced Training Cong Fang Hangfeng He Qi Long Weijie J. Su FAtt 124 165 0 29 Jan 2021
Neural Mechanics: Symmetry and Broken Conservation Laws in Deep Learning Dynamics D. Kunin Javier Sagastuy-Breña Surya Ganguli Daniel L. K. Yamins Hidenori Tanaka 101 77 0 08 Dec 2020