ResearchTrend.AI
Quasi-potential as an implicit regularizer for the loss function in the stochastic gradient descent

Quasi-potential as an implicit regularizer for the loss function in the stochastic gradient descent

Wenqing Hu
Zhanxing Zhu
Haoyi Xiong
Jun Huan
    MLT
ArXivPDFHTML

Papers citing "Quasi-potential as an implicit regularizer for the loss function in the stochastic gradient descent"

3 / 3 papers shown
Title
Exponential escape efficiency of SGD from sharp minima in non-stationary regime
Exponential escape efficiency of SGD from sharp minima in non-stationary regime
Hikaru Ibayashi
Masaaki Imaizumi
34
4
0
07 Nov 2021
On the Noisy Gradient Descent that Generalizes as SGD
On the Noisy Gradient Descent that Generalizes as SGD
Jingfeng Wu
Wenqing Hu
Haoyi Xiong
Jun Huan
Vladimir Braverman
Zhanxing Zhu
MLT
24
10
0
18 Jun 2019
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima
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
312
2,896
0
15 Sep 2016