English

Online Statistical Inference for Nonlinear Stochastic Approximation with Markovian Data

Statistics Theory 2023-02-21 v2 Methodology Machine Learning Statistics Theory

Abstract

We study the statistical inference of nonlinear stochastic approximation algorithms utilizing a single trajectory of Markovian data. Our methodology has practical applications in various scenarios, such as Stochastic Gradient Descent (SGD) on autoregressive data and asynchronous Q-Learning. By utilizing the standard stochastic approximation (SA) framework to estimate the target parameter, we establish a functional central limit theorem for its partial-sum process, ϕT\boldsymbol{\phi}_T. To further support this theory, we provide a matching semiparametric efficient lower bound and a non-asymptotic upper bound on its weak convergence, measured in the L\'evy-Prokhorov metric. This functional central limit theorem forms the basis for our inference method. By selecting any continuous scale-invariant functional ff, the asymptotic pivotal statistic f(ϕT)f(\boldsymbol{\phi}_T) becomes accessible, allowing us to construct an asymptotically valid confidence interval. We analyze the rejection probability of a family of functionals fmf_m, indexed by mNm \in \mathbb{N}, through theoretical and numerical means. The simulation results demonstrate the validity and efficiency of our method.

Keywords

Cite

@article{arxiv.2302.07690,
  title  = {Online Statistical Inference for Nonlinear Stochastic Approximation with Markovian Data},
  author = {Xiang Li and Jiadong Liang and Zhihua Zhang},
  journal= {arXiv preprint arXiv:2302.07690},
  year   = {2023}
}
R2 v1 2026-06-28T08:40:47.181Z