Stochastic Approximation Proximal Method of Multipliers for Convex Stochastic Programming
Abstract
This paper considers the problem of minimizing a convex expectation function over a closed convex set, coupled with a set of inequality convex expectation constraints. We present a new stochastic approximation type algorithm, namely the stochastic approximation proximal method of multipliers (PMMSopt) to solve this convex stochastic optimization problem. We analyze regrets of a stochastic approximation proximal method of multipliers for solving convex stochastic optimization problems. Under mild conditions, we show that this algorithm exhibits rate of convergence, in terms of both optimality gap and constraint violation if parameters in the algorithm are properly chosen, when the objective and constraint functions are generally convex, where denotes the number of iterations. Moreover, we show that, with at least probability, the algorithm has no more than objective regret and no more than constraint violation regret. To the best of our knowledge, this is the first time that such a proximal method for solving expectation constrained stochastic optimization is presented in the literature.
Cite
@article{arxiv.1907.12226,
title = {Stochastic Approximation Proximal Method of Multipliers for Convex Stochastic Programming},
author = {Liwei Zhang and Yule Zhang and Jia Wu},
journal= {arXiv preprint arXiv:1907.12226},
year = {2020}
}