Greg Yang

activity

20222025

most citedHigh-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation

11 citations · 13 across the 5 of their papers we have counts for

collaborators

Showing cs.LGShow all

2 papers · 1 filter

cs.LG2025

Global Convergence and Rich Feature Learning in $L$ -Layer Infinite-Width Neural Networks under $μ$ P Parametrization

Zixiang Chen, Greg Yang, Qingyue Zhao +1

Despite deep neural networks' powerful representation learning capabilities, theoretical understanding of how networks can simultaneously achieve meaningful feature learning and gl…

cs.LG2023

A Spectral Condition for Feature Learning

Greg Yang, James B. Simon, Jeremy Bernstein

The push to train ever larger neural networks has motivated the study of initialization and training at large network width. A key challenge is to scale training so that a network'…

Global Convergence and Rich Feature Learning in L-Layer Infinite-Width Neural Networks under μP Parametrization

A Spectral Condition for Feature Learning

Global Convergence and Rich Feature Learning in $L$ -Layer Infinite-Width Neural Networks under $μ$ P Parametrization