PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex Optimization

Zhize Li, Hongyan Bao, Xiangliang Zhang, Peter Richtarik

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we propose a novel stochastic gradient estimator-ProbAbilistic Gradient Estimator (PAGE)-for nonconvex optimization. PAGE is easy to implement as it is designed via a small adjustment to vanilla SGD: in each iteration, PAGE uses the vanilla minibatch SGD update with probability p t or reuses the previous gradient with a small adjustment, at a much lower computational cost, with probability 1 - p(t). We give a simple formula for the optimal choice of p(t). Moreover, we prove the first tight lower bound Omega (n + root n/epsilon(2)), for non-convex finite-sum problems, which also leads to a tight lower bound Omega (b + root b/epsilon(2)) for non- convex online problems, where b := min{sigma(2)/epsilon(2), n} . Then, we show that PAGE obtains the optimal convergence results O(n + root n/epsilon(2)) (finite-sum) and O(b + root b/is an element of(2)) (online) matching our lower bounds for both nonconvex finite-sum and online problems. Besides, we also show that for nonconvex functions satisfying the Polyak-Lojasiewicz (PL) condition, PAGE can automatically switch to a faster linear convergence rate O(. log 1/epsilon). Finally, we conduct several deep learning experiments (e.g., LeNet, VGG, ResNet) on real datasets in PyTorch showing that PAGE not only converges much faster than SGD in training but also achieves the higher test accuracy, validating the optimal theoretical results and confirming the practical superiority of PAGE.
Original languageEnglish (US)
Title of host publicationInternational Conference on Machine Learning (ICML)
PublisherarXiv
StatePublished - 2021

Fingerprint

Dive into the research topics of 'PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex Optimization'. Together they form a unique fingerprint.

Cite this