Stochastic Approximation Proximal Method of Multipliers for Convex Stochastic Programming
From MaRDI portal
Publication:6199237
DOI10.1287/MOOR.2022.1257arXiv1907.12226OpenAlexW2964718684WikidataQ114058150 ScholiaQ114058150MaRDI QIDQ6199237
Jia Wu, Yu-Le Zhang, Li-wei Zhang, Xiantao Xiao
Publication date: 23 February 2024
Published in: Mathematics of Operations Research (Search for Journal in Brave)
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 ${
m O}(T^{-1/2})$ 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 $T$ denotes the number of iterations. Moreover, we show that, with at least $1-e^{-T^{1/4}}$ probability, the algorithm has no more than ${
m O}(T^{-1/4})$ objective regret and no more than ${
m O}(T^{-1/8})$ 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.
Full work available at URL: https://arxiv.org/abs/1907.12226
stochastic approximationconvex stochastic optimizationproximal method of multipliersconstraint violation regrethigh probability regret boundobjective regret
Nonlinear programming (90C30) Stochastic programming (90C15) Numerical methods based on nonlinear programming (49M37)
This page was built for publication: Stochastic Approximation Proximal Method of Multipliers for Convex Stochastic Programming
