Papers
Communities
Events
Blog
Pricing
Search
Open menu
Home
Papers
2111.04004
Cited By
Exponential escape efficiency of SGD from sharp minima in non-stationary regime
7 November 2021
Hikaru Ibayashi
Masaaki Imaizumi
Re-assign community
ArXiv
PDF
HTML
Papers citing
"Exponential escape efficiency of SGD from sharp minima in non-stationary regime"
4 / 4 papers shown
Title
A Quadratic Synchronization Rule for Distributed Deep Learning
Xinran Gu
Kaifeng Lyu
Sanjeev Arora
Jingzhao Zhang
Longbo Huang
36
1
0
22 Oct 2023
Decentralized SGD and Average-direction SAM are Asymptotically Equivalent
Tongtian Zhu
Fengxiang He
Kaixuan Chen
Mingli Song
Dacheng Tao
34
15
0
05 Jun 2023
Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction
Kaifeng Lyu
Zhiyuan Li
Sanjeev Arora
FAtt
22
55
0
14 Jun 2022
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima
N. Keskar
Dheevatsa Mudigere
J. Nocedal
M. Smelyanskiy
P. T. P. Tang
ODL
273
2,878
0
15 Sep 2016
1