A Regression-Based Prediction-Correction Method for Stochastic Time-Varying Optimization Problems

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kamijima, Tomoya, Marumo, Naoki, Takeda, Akiko
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915681442725888
author Kamijima, Tomoya
Marumo, Naoki
Takeda, Akiko
author_facet Kamijima, Tomoya
Marumo, Naoki
Takeda, Akiko
contents In many real-world applications, optimization problems evolve continuously over time and are often subject to stochastic noise. We consider a stochastic time-varying optimization problem in which the objective function $f(x;t)$ changes continuously and only noisy gradient observations are available. In deterministic settings, the prediction-correction method that exploits the time derivative of the solution is effective for accurately tracking the solution trajectory. However, a straightforward extension to stochastic problems requires an estimate of $\nabla_{xt} f(x;t)$ and the computation of a Hessian inverse at each step--requirements that are difficult or costly in practice. To address these issues, we propose a prediction-correction algorithm that uses a regression-based prediction step: the prediction is formed as a linear combination of recent iterates, which can be computed efficiently without estimating $\nabla_{xt}f(x;t)$ or computing Hessian inversions. We prove a tracking-error bound for the proposed method under standard smoothness and stochastic assumptions. Numerical experiments show that the regression-based prediction improves tracking accuracy while reducing computational cost compared with existing methods.
format Preprint
id arxiv_https___arxiv_org_abs_2512_15205
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Regression-Based Prediction-Correction Method for Stochastic Time-Varying Optimization Problems
Kamijima, Tomoya
Marumo, Naoki
Takeda, Akiko
Optimization and Control
90C15, 90C25, 65K05
In many real-world applications, optimization problems evolve continuously over time and are often subject to stochastic noise. We consider a stochastic time-varying optimization problem in which the objective function $f(x;t)$ changes continuously and only noisy gradient observations are available. In deterministic settings, the prediction-correction method that exploits the time derivative of the solution is effective for accurately tracking the solution trajectory. However, a straightforward extension to stochastic problems requires an estimate of $\nabla_{xt} f(x;t)$ and the computation of a Hessian inverse at each step--requirements that are difficult or costly in practice. To address these issues, we propose a prediction-correction algorithm that uses a regression-based prediction step: the prediction is formed as a linear combination of recent iterates, which can be computed efficiently without estimating $\nabla_{xt}f(x;t)$ or computing Hessian inversions. We prove a tracking-error bound for the proposed method under standard smoothness and stochastic assumptions. Numerical experiments show that the regression-based prediction improves tracking accuracy while reducing computational cost compared with existing methods.
title A Regression-Based Prediction-Correction Method for Stochastic Time-Varying Optimization Problems
topic Optimization and Control
90C15, 90C25, 65K05
url https://arxiv.org/abs/2512.15205