A Local Convergence Theory for the Stochastic Gradient Descent Method in Non-Convex Optimization With Non-isolated Local Minima

Abstract

Non-convex loss functions arise frequently in modern machine learning, and for the theoretical analysis of stochastic optimization methods, the presence of non-isolated minima presents a unique challenge that has remained under-explored. In this paper, we study the local convergence of the stochastic gradient descent method to non-isolated global minima. Under mild assumptions, we estimate the probability for the iterations to stay near the minima by adopting the notion of stochastic stability. After establishing such stability, we present the lower bound complexity in terms of various error criteria for a given error tolerance ǫ and a failure probability γ.