On Graduated Optimization for Stochastic Non-Convex Problems
Abstract
The graduated optimization approach, also known as the continuation method, is a popular heuristic to solving non-convex problems that has received renewed interest over the last decade. Despite its popularity, very little is known in terms of theoretical convergence analysis. In this paper we describe a new first-order algorithm based on graduated optimiza- tion and analyze its performance. We characterize a parameterized family of non- convex functions for which this algorithm provably converges to a global optimum. In particular, we prove that the algorithm converges to an {\epsilon}-approximate solution within O(1/\epsilon^2) gradient-based steps. We extend our algorithm and analysis to the setting of stochastic non-convex optimization with noisy gradient feedback, attaining the same convergence rate. Additionally, we discuss the setting of zero-order optimization, and devise a a variant of our algorithm which converges at rate of O(d^2/\epsilon^4).
Cite
@article{arxiv.1503.03712,
title = {On Graduated Optimization for Stochastic Non-Convex Problems},
author = {Elad Hazan and Kfir Y. Levy and Shai Shalev-Shwartz},
journal= {arXiv preprint arXiv:1503.03712},
year = {2015}
}
Comments
17 pages