Kernel machines that adapt to GPUs for effective large batch training

15 June 2018

Papers citing "Kernel machines that adapt to GPUs for effective large batch training"

4 / 4 papers shown

Title
The Power of Interpolation: Understanding the Effectiveness of SGD in Modern Over-parametrized Learning Siyuan Ma Raef Bassily M. Belkin 45 289 0 18 Dec 2017
Don't Decay the Learning Rate, Increase the Batch Size Samuel L. Smith Pieter-Jan Kindermans Chris Ying Quoc V. Le ODL 90 990 0 01 Nov 2017
One weird trick for parallelizing convolutional neural networks A. Krizhevsky GNN 69 1,297 0 23 Apr 2014
Mini-Batch Primal and Dual Methods for SVMs Martin Takáč A. Bijral Peter Richtárik Nathan Srebro 50 195 0 10 Mar 2013