On the Convergence to a Global Solution of Shuffling-Type Gradient Algorithms

Lam M. Nguyen, Trang H. Tran

Keywords: stochastic gradient, shuffling type gradient method, global convergence

TL;DR: We investigate a new framework for the convergence of shuffling-type gradient algorithm to a global solution under some conditions.

Abstract: Stochastic gradient descent (SGD) algorithm is the method of choice in many machine learning tasks thanks to its scalability and efficiency in dealing with large-scale problems. In this paper, we focus on the shuffling version of SGD which matches the mainstream practical heuristics. We show the convergence to a global solution of shuffling SGD for a class of non-convex functions under over-parameterized settings. Our analysis employs more relaxed non-convex assumptions than previous literature. Nevertheless, we maintain the desired computational complexity as shuffling SGD has achieved in the general convex setting.

Submission Number: 8949