On the Outsized Importance of Learning Rates in Local Update Methods

2 July 2020

Papers citing "On the Outsized Importance of Learning Rates in Local Update Methods"

5 / 55 papers shown

Title
Optimization Methods for Large-Scale Machine Learning Léon Bottou Frank E. Curtis J. Nocedal 252 3,226 0 15 Jun 2016
Communication-Efficient Learning of Deep Networks from Decentralized Data H. B. McMahan Eider Moore Daniel Ramage S. Hampson Blaise Agüera y Arcas FedML 408 17,615 0 17 Feb 2016
Adam: A Method for Stochastic Optimization Diederik P. Kingma Jimmy Ba ODL 2.1K 150,364 0 22 Dec 2014
One weird trick for parallelizing convolutional neural networks A. Krizhevsky GNN 93 1,303 0 23 Apr 2014
Making Gradient Descent Optimal for Strongly Convex Stochastic Optimization Alexander Rakhlin Ohad Shamir Karthik Sridharan 178 769 0 26 Sep 2011