Papers
Communities
Events
Blog
Pricing
Search
Open menu
Home
Papers
2102.05375
Cited By
v1
v2
v3 (latest)
Strength of Minibatch Noise in SGD
10 February 2021
Liu Ziyin
Kangqiao Liu
Takashi Mori
Masakuni Ueda
ODL
MLT
Re-assign community
ArXiv (abs)
PDF
HTML
Papers citing
"Strength of Minibatch Noise in SGD"
10 / 10 papers shown
Title
SGD as Free Energy Minimization: A Thermodynamic View on Neural Network Training
Ildus Sadrtdinov
Ivan Klimov
E. Lobacheva
Dmitry Vetrov
28
0
0
29 May 2025
Decentralized SGD and Average-direction SAM are Asymptotically Equivalent
Tongtian Zhu
Fengxiang He
Kaixuan Chen
Mingli Song
Dacheng Tao
154
15
0
05 Jun 2023
Evolutionary Algorithms in the Light of SGD: Limit Equivalence, Minima Flatness, and Transfer Learning
Andrei Kucharavy
R. Guerraoui
Ljiljana Dolamic
104
1
0
20 May 2023
Training trajectories, mini-batch losses and the curious role of the learning rate
Mark Sandler
A. Zhmoginov
Max Vladymyrov
Nolan Miller
ODL
85
12
0
05 Jan 2023
On the Overlooked Structure of Stochastic Gradients
Zeke Xie
Qian-Yuan Tang
Mingming Sun
P. Li
94
6
0
05 Dec 2022
Two Facets of SDE Under an Information-Theoretic Lens: Generalization of SGD via Training Trajectories and via Terminal States
Ziqiao Wang
Yongyi Mao
111
12
0
19 Nov 2022
Noise Injection Node Regularization for Robust Learning
N. Levi
I. Bloch
M. Freytsis
T. Volansky
AI4CE
64
2
0
27 Oct 2022
SGD with Large Step Sizes Learns Sparse Features
Maksym Andriushchenko
Aditya Varre
Loucas Pillaud-Vivien
Nicolas Flammarion
143
60
0
11 Oct 2022
Stochastic Neural Networks with Infinite Width are Deterministic
Liu Ziyin
Hanlin Zhang
Xiangming Meng
Yuting Lu
Eric P. Xing
Masakuni Ueda
91
3
0
30 Jan 2022
SGD with a Constant Large Learning Rate Can Converge to Local Maxima
Liu Ziyin
Botao Li
James B. Simon
Masakuni Ueda
88
9
0
25 Jul 2021
1