Rethinking Adam: A Twofold Exponential Moving Average Approach

22 June 2021

Huan Wang

Papers citing "Rethinking Adam: A Twofold Exponential Moving Average Approach"

1 / 1 papers shown

Title
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 310 2,896 0 15 Sep 2016