Random Reshuffling: Simple Analysis with Vast Improvements

arXiv2006.05988MaRDI QIDQ6342566

Author name not available (Why is that?)

Publication date: 10 June 2020

Abstract: Random Reshuffling (RR) is an algorithm for minimizing finite-sum functions that utilizes iterative gradient descent steps in conjunction with data reshuffling. Often contrasted with its sibling Stochastic Gradient Descent (SGD), RR is usually faster in practice and enjoys significant popularity in convex and non-convex optimization. The convergence rate of RR has attracted substantial attention recently and, for strongly convex and smooth functions, it was shown to converge faster than SGD if 1) the stepsize is small, 2) the gradients are bounded, and 3) the number of epochs is large. We remove these 3 assumptions, improve the dependence on the condition number from $kapp{a}^2$ to $kappa$ (resp. from $kappa$ to $sqrtkappa$) and, in addition, show that RR has a different type of variance. We argue through theory and experiments that the new variance type gives an additional justification of the superior performance of RR. To go beyond strong convexity, we present several results for non-strongly convex and non-convex objectives. We show that in all cases, our theory improves upon existing literature. Finally, we prove fast convergence of the Shuffle-Once (SO) algorithm, which shuffles the data only once, at the beginning of the optimization process. Our theory for strongly-convex objectives tightly matches the known lower bounds for both RR and SO and substantiates the common practical heuristic of shuffling once or only a few times. As a byproduct of our analysis, we also get new results for the Incremental Gradient algorithm (IG), which does not shuffle the data at all.

Has companion code repository: https://github.com/konstmish/random_reshuffling

This page was built for publication: Random Reshuffling: Simple Analysis with Vast Improvements

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6342566)