Finite-time High-probability Bounds for Polyak-Ruppert Averaged Iterates of Linear Stochastic Approximation

arXiv2207.04475MaRDI QIDQ6404524FDOQ6404524

Authors: Alain Durmus, Eric Moulines, Alexey Naumov, S. P. Samsonov 

Publication date: 10 July 2022

Abstract: This paper provides a finite-time analysis of linear stochastic approximation (LSA) algorithms with fixed step size, a core method in statistics and machine learning. LSA is used to compute approximate solutions of a $d$-dimensional linear system $$ for which $$ can only be estimated by (asymptotically) unbiased observations ${(mathbfA(Z_n),mathbfb(Z_n))}_{ninmathbbN}$. We consider here the case where ${Z_n}_{ninmathbbN}$ is an i.i.d. sequence or a uniformly geometrically ergodic Markov chain. We derive $p$-th moment and high-probability deviation bounds for the iterates defined by LSA and its Polyak-Ruppert-averaged version. Our finite-time instance-dependent bounds for the averaged LSA iterates are sharp in the sense that the leading term we obtain coincides with the local asymptotic minimax limit. Moreover, the remainder terms of our bounds admit a tight dependence on the mixing time $t_{operatornamemix}$ of the underlying chain and the norm of the noise variables. We emphasize that our result requires the SA step size to scale only with logarithm of the problem dimension $d$.

Mathematics Subject Classification ID

Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Stochastic approximation (62L20)

This page was built for publication: Finite-time High-probability Bounds for Polyak-Ruppert Averaged Iterates of Linear Stochastic Approximation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6404524)