Random Shuffling Beats SGD after Finite Epochs

作者: Jeff Haochen, Suvrit Sra

摘要

A long-standing problem in stochastic optimization is proving that \rsgd, the without-replacement version of \sgd, converges faster than the usual with-replacement \sgd. Building upon \citep{gurbuzbalaban2015random}, we present the

PDF打开原文