Stochastic Approximation for Expectation Objective and Expectation Inequality-Constrained Nonconvex Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Facchinei, Francisco, Kungurtsev, Vyacheslav
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916865275592704
author Facchinei, Francisco
Kungurtsev, Vyacheslav
author_facet Facchinei, Francisco
Kungurtsev, Vyacheslav
contents Stochastic Approximation has been a prominent set of tools for solving problems with noise and uncertainty. Increasingly, it becomes important to solve optimization problems wherein there is noise in both a set of constraints that a practitioner requires the system to adhere to, as well as the objective, which typically involves some empirical loss. We present the first stochastic approximation approach for solving this class of problems using the Ghost framework of incorporating penalty functions for analysis of a sequential convex programming approach together with a Monte Carlo estimator of nonlinear maps. We provide almost sure convergence guarantees and demonstrate the performance of the procedure on some representative examples.
format Preprint
id arxiv_https___arxiv_org_abs_2307_02943
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Stochastic Approximation for Expectation Objective and Expectation Inequality-Constrained Nonconvex Optimization
Facchinei, Francisco
Kungurtsev, Vyacheslav
Optimization and Control
Stochastic Approximation has been a prominent set of tools for solving problems with noise and uncertainty. Increasingly, it becomes important to solve optimization problems wherein there is noise in both a set of constraints that a practitioner requires the system to adhere to, as well as the objective, which typically involves some empirical loss. We present the first stochastic approximation approach for solving this class of problems using the Ghost framework of incorporating penalty functions for analysis of a sequential convex programming approach together with a Monte Carlo estimator of nonlinear maps. We provide almost sure convergence guarantees and demonstrate the performance of the procedure on some representative examples.
title Stochastic Approximation for Expectation Objective and Expectation Inequality-Constrained Nonconvex Optimization
topic Optimization and Control
url https://arxiv.org/abs/2307.02943