A Functional Model Method for Nonconvex Nonsmooth Conditional Stochastic Optimization

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Ruszczyński, Andrzej, Yang, Shangzhe
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910450956894208
author Ruszczyński, Andrzej
Yang, Shangzhe
author_facet Ruszczyński, Andrzej
Yang, Shangzhe
contents We consider stochastic optimization problems involving an expected value of a nonlinear function of a base random vector and a conditional expectation of another function depending on the base random vector, a dependent random vector, and the decision variables. We call such problems conditional stochastic optimization problems. They arise in many applications, such as uplift modeling, reinforcement learning, and contextual optimization. We propose a specialized single time-scale stochastic method for nonconvex constrained conditional stochastic optimization problems with a Lipschitz smooth outer function and a generalized differentiable inner function. In the method, we approximate the inner conditional expectation with a rich parametric model whose mean squared error satisfies a stochastic version of a Łojasiewicz condition. The model is used by an inner learning algorithm. The main feature of our approach is that unbiased stochastic estimates of the directions used by the method can be generated with one observation from the joint distribution per iteration, which makes it applicable to real-time learning. The directions, however, are not gradients or subgradients of any overall objective function. We prove the convergence of the method with probability one, using the method of differential inclusions and a specially designed Lyapunov function, involving a stochastic generalization of the Bregman distance. Finally, a numerical illustration demonstrates the viability of our approach.
format Preprint
id arxiv_https___arxiv_org_abs_2405_10815
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Functional Model Method for Nonconvex Nonsmooth Conditional Stochastic Optimization
Ruszczyński, Andrzej
Yang, Shangzhe
Optimization and Control
Machine Learning
90C15, 49J52, 60-08
We consider stochastic optimization problems involving an expected value of a nonlinear function of a base random vector and a conditional expectation of another function depending on the base random vector, a dependent random vector, and the decision variables. We call such problems conditional stochastic optimization problems. They arise in many applications, such as uplift modeling, reinforcement learning, and contextual optimization. We propose a specialized single time-scale stochastic method for nonconvex constrained conditional stochastic optimization problems with a Lipschitz smooth outer function and a generalized differentiable inner function. In the method, we approximate the inner conditional expectation with a rich parametric model whose mean squared error satisfies a stochastic version of a Łojasiewicz condition. The model is used by an inner learning algorithm. The main feature of our approach is that unbiased stochastic estimates of the directions used by the method can be generated with one observation from the joint distribution per iteration, which makes it applicable to real-time learning. The directions, however, are not gradients or subgradients of any overall objective function. We prove the convergence of the method with probability one, using the method of differential inclusions and a specially designed Lyapunov function, involving a stochastic generalization of the Bregman distance. Finally, a numerical illustration demonstrates the viability of our approach.
title A Functional Model Method for Nonconvex Nonsmooth Conditional Stochastic Optimization
topic Optimization and Control
Machine Learning
90C15, 49J52, 60-08
url https://arxiv.org/abs/2405.10815