Accelerating Stochastic Composition Optimization
Abstract
Consider the stochastic 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, which updates based on queries to the sampling oracle using two different timescales. 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 further demonstrate the application of ASC-PG to reinforcement learning and conduct numerical experiments.
Cite
@article{arxiv.1607.07329,
title = {Accelerating Stochastic Composition Optimization},
author = {Mengdi Wang and Ji Liu and Ethan X. Fang},
journal= {arXiv preprint arXiv:1607.07329},
year = {2016}
}