Noise Regularizes Over-parameterized Rank One Matrix Recovery, Provably

7 February 2022

Papers citing "Noise Regularizes Over-parameterized Rank One Matrix Recovery, Provably"

2 / 2 papers shown

Title
Large Learning Rate Tames Homogeneity: Convergence and Balancing Effect Yuqing Wang Minshuo Chen T. Zhao Molei Tao AI4CE 55 40 0 07 Oct 2021
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