Revisiting the Constant Stepsize Stochastic Approximation with Decision-Dependent Markovian Noise

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Hadavi, Hadi, Mou, Wenlong, Samsonov, Sergey, Wai, Hoi-To
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915937928609792
author Hadavi, Hadi
Mou, Wenlong
Samsonov, Sergey
Wai, Hoi-To
author_facet Hadavi, Hadi
Mou, Wenlong
Samsonov, Sergey
Wai, Hoi-To
contents We revisit the convergence analysis of constant stepsize stochastic approximation (SA) with decision-dependent Markovian noise, with a focus on characterizing the stationary bias against the root of the mean-field equation. We first establish the finite-time $p$-th moment bounds for the SA iterates in a general decision-dependent setting, which serve as a stability foundation for the subsequent analysis. Building on this foundation, and leveraging a local regularity condition termed Poisson--Gateaux differentiability (WD$^\ast$) for the solution to Poisson equation induced by the decision-dependent Markov kernel, we show that the stationary bias is of the order $\mathcal{O}(α)$ for a broad class of decision-dependent settings. Additionally, we establish geometric weak convergence of the joint SA process towards a unique stationary distribution, and a functional central limit theorem. Our relaxed regularity condition enables us to cover cases of non-smooth kernels such as acceptance--rejection mechanisms, projected Langevin dynamics, and clipped state dynamics.
format Preprint
id arxiv_https___arxiv_org_abs_2604_13378
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Revisiting the Constant Stepsize Stochastic Approximation with Decision-Dependent Markovian Noise
Hadavi, Hadi
Mou, Wenlong
Samsonov, Sergey
Wai, Hoi-To
Optimization and Control
We revisit the convergence analysis of constant stepsize stochastic approximation (SA) with decision-dependent Markovian noise, with a focus on characterizing the stationary bias against the root of the mean-field equation. We first establish the finite-time $p$-th moment bounds for the SA iterates in a general decision-dependent setting, which serve as a stability foundation for the subsequent analysis. Building on this foundation, and leveraging a local regularity condition termed Poisson--Gateaux differentiability (WD$^\ast$) for the solution to Poisson equation induced by the decision-dependent Markov kernel, we show that the stationary bias is of the order $\mathcal{O}(α)$ for a broad class of decision-dependent settings. Additionally, we establish geometric weak convergence of the joint SA process towards a unique stationary distribution, and a functional central limit theorem. Our relaxed regularity condition enables us to cover cases of non-smooth kernels such as acceptance--rejection mechanisms, projected Langevin dynamics, and clipped state dynamics.
title Revisiting the Constant Stepsize Stochastic Approximation with Decision-Dependent Markovian Noise
topic Optimization and Control
url https://arxiv.org/abs/2604.13378