Campus Units

Electrical and Computer Engineering

Document Type

Article

Publication Version

Submitted Manuscript

Publication Date

2020

Journal or Book Title

arXiv

Abstract

The alternating gradient descent (AGD) is a simple but popular algorithm which has been applied to problems in optimization, machine learning, data ming, and signal processing, etc. The algorithm updates two blocks of variables in an alternating manner, in which a gradient step is taken on one block, while keeping the remaining block fixed. When the objective function is nonconvex, it is well-known the AGD converges to the first-order stationary solution with a global sublinear rate.
In this paper, we show that a variant of AGD-type algorithms will not be trapped by "bad" stationary solutions such as saddle points and local maximum points. In particular, we consider a smooth unconstrained optimization problem, and propose a perturbed AGD (PA-GD) which converges (with high probability) to the set of second-order stationary solutions (SS2) with a global sublinear rate. To the best of our knowledge, this is the first alternating type algorithm which takes O(polylog(d)/ϵ7/3) iterations to achieve SS2 with high probability [where polylog(d) is polynomial of the logarithm of dimension d of the problem].

Comments

This is a pre-print of the article Lu, Songtao, Mingyi Hong, and Zhengdao Wang. "On the sublinear convergence of randomly perturbed alternating gradient descent to second order stationary solutions." arXiv preprint arXiv:1802.10418 (2018). Posted with permission.

Copyright Owner

The Author(s)

Language

en

File Format

application/pdf

Published Version

Share

COinS