Skip to main content

Accelerating Stochastic Composition Optimization

Author(s): Wang, Mengdi; Liu, Ji; Fang, Ethan X.

To refer to this page use:
Abstract: We consider the stochastic nested composition optimization problem where the objective is a composition of two expected-value functions. We propose a new stochastic first-order method, namely the accelerated stochastic compositional proximal gradient (ASC-PG) method. This algorithm updates the solution based on noisy gradient queries using a two-timescale iteration. The ASC-PG is the first proximal gradient method for the stochastic composition problem that can deal with nonsmooth regularization penalty. We show that the ASC-PG exhibits faster convergence than the best known algorithms, and that it achieves the optimal sample-error complexity in several important special cases. We demonstrate the application of ASC-PG to reinforcement learning and conduct numerical experiments.
Publication Date: 17-Oct-2017
Citation: Wang, Mengdi, Ji Liu, and Ethan X. Fang. "Accelerating stochastic composition optimization." The Journal of Machine Learning Research 18, no. 1 (2017): 3721-3743.
ISSN: 1532-4435
EISSN: 1533-7928
Pages: 3721 - 3743
Type of Material: Journal Article
Journal/Proceeding Title: Journal of Machine Learning Research
Version: Final published version. This is an open access article.

Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.