Convergence Rate in Nonlinear Two-Time-Scale Stochastic Approximation with State (Time)-Dependence

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chen, Zixi, Xu, Yumin, Zhang, Ruixun
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908538220052480
author Chen, Zixi
Xu, Yumin
Zhang, Ruixun
author_facet Chen, Zixi
Xu, Yumin
Zhang, Ruixun
contents The nonlinear two-time-scale stochastic approximation is widely studied under conditions of bounded variances in noise. Motivated by recent advances that allow for variability linked to the current state or time, we consider state- and time-dependent noises. We show that the Lyapunov function exhibits polynomial convergence rates in both cases, with the rate of polynomial delay depending on the parameters of state- or time-dependent noises. Notably, if the state noise parameters fully approach their limiting value, the Lyapunov function achieves an exponential convergence rate. We provide two numerical examples to illustrate our theoretical findings in the context of stochastic gradient descent with Polyak-Ruppert averaging and stochastic bilevel optimization.
format Preprint
id arxiv_https___arxiv_org_abs_2509_11039
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Convergence Rate in Nonlinear Two-Time-Scale Stochastic Approximation with State (Time)-Dependence
Chen, Zixi
Xu, Yumin
Zhang, Ruixun
Optimization and Control
Machine Learning
The nonlinear two-time-scale stochastic approximation is widely studied under conditions of bounded variances in noise. Motivated by recent advances that allow for variability linked to the current state or time, we consider state- and time-dependent noises. We show that the Lyapunov function exhibits polynomial convergence rates in both cases, with the rate of polynomial delay depending on the parameters of state- or time-dependent noises. Notably, if the state noise parameters fully approach their limiting value, the Lyapunov function achieves an exponential convergence rate. We provide two numerical examples to illustrate our theoretical findings in the context of stochastic gradient descent with Polyak-Ruppert averaging and stochastic bilevel optimization.
title Convergence Rate in Nonlinear Two-Time-Scale Stochastic Approximation with State (Time)-Dependence
topic Optimization and Control
Machine Learning
url https://arxiv.org/abs/2509.11039