Finite-Time Decoupled Convergence in Nonlinear Two-Time-Scale Stochastic Approximation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Han, Yuze, Li, Xiang, Zhang, Zhihua
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914465105051648
author Han, Yuze
Li, Xiang
Zhang, Zhihua
author_facet Han, Yuze
Li, Xiang
Zhang, Zhihua
contents In two-time-scale stochastic approximation (SA), two iterates are updated at varying speeds using different step sizes, with each update influencing the other. Previous studies on linear two-time-scale SA have shown that the convergence rates of the mean-square errors for these updates depend solely on their respective step sizes, a phenomenon termed decoupled convergence. However, achieving decoupled convergence in nonlinear SA remains less understood. Our research investigates the potential for finite-time decoupled convergence in nonlinear two-time-scale SA. We demonstrate that, under a nested local linearity assumption, finite-time decoupled convergence rates can be achieved with suitable step size selection. To derive this result, we conduct a convergence analysis of the matrix cross term between the iterates and leverage fourth-order moment convergence rates to control the higher-order error terms induced by local linearity. To further investigate the necessity of local linearity for decoupled convergence, we also construct an example showing that, even when the fast-time-scale update is linear, the nonlinearity of the slow-time-scale update alone can destroy decoupled convergence.
format Preprint
id arxiv_https___arxiv_org_abs_2401_03893
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Finite-Time Decoupled Convergence in Nonlinear Two-Time-Scale Stochastic Approximation
Han, Yuze
Li, Xiang
Zhang, Zhihua
Optimization and Control
Machine Learning
In two-time-scale stochastic approximation (SA), two iterates are updated at varying speeds using different step sizes, with each update influencing the other. Previous studies on linear two-time-scale SA have shown that the convergence rates of the mean-square errors for these updates depend solely on their respective step sizes, a phenomenon termed decoupled convergence. However, achieving decoupled convergence in nonlinear SA remains less understood. Our research investigates the potential for finite-time decoupled convergence in nonlinear two-time-scale SA. We demonstrate that, under a nested local linearity assumption, finite-time decoupled convergence rates can be achieved with suitable step size selection. To derive this result, we conduct a convergence analysis of the matrix cross term between the iterates and leverage fourth-order moment convergence rates to control the higher-order error terms induced by local linearity. To further investigate the necessity of local linearity for decoupled convergence, we also construct an example showing that, even when the fast-time-scale update is linear, the nonlinearity of the slow-time-scale update alone can destroy decoupled convergence.
title Finite-Time Decoupled Convergence in Nonlinear Two-Time-Scale Stochastic Approximation
topic Optimization and Control
Machine Learning
url https://arxiv.org/abs/2401.03893