Stochastic Training is Not Necessary for Generalization

29 September 2021

Papers citing "Stochastic Training is Not Necessary for Generalization"

5 / 5 papers shown

Title
Gradient Descent as a Shrinkage Operator for Spectral Bias Simon Lucey 22 0 0 25 Apr 2025
Neural Redshift: Random Networks are not Random Functions Damien Teney A. Nicolicioiu Valentin Hartmann Ehsan Abbasnejad 75 18 0 04 Mar 2024
The large learning rate phase of deep learning: the catapult mechanism Aitor Lewkowycz Yasaman Bahri Ethan Dyer Jascha Narain Sohl-Dickstein Guy Gur-Ari ODL 140 198 0 04 Mar 2020
Bag of Tricks for Image Classification with Convolutional Neural Networks Tong He Zhi-Li Zhang Hang Zhang Zhongyue Zhang Junyuan Xie Mu Li 197 1,275 0 04 Dec 2018
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 270 2,696 0 15 Sep 2016