Characterizing Dynamical Stability of Stochastic Gradient Descent in Overparameterized Learning

29 July 2024

Papers citing "Characterizing Dynamical Stability of Stochastic Gradient Descent in Overparameterized Learning"

2 / 2 papers shown

Title
Understanding Gradient Descent on Edge of Stability in Deep Learning Sanjeev Arora Zhiyuan Li A. Panigrahi MLT 80 89 0 19 May 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 281 2,889 0 15 Sep 2016