paper-with-me

홈 › Papers

Concentration of Contractive Stochastic Approximation: Additive and Multiplicative Noise

2023-03-28 · Zaiwei Chen, Siva Theja Maguluri, Martin Zubeldia

In this paper, we establish maximal concentration bounds for the iterates generated by a stochastic approximation (SA) algorithm under a contractive operator with respect to some arbitrary norm (for example, the $\ell_\infty$-norm). We consider two settings where the iterates are potentially unbounded: SA with bounded multiplicative noise and SA with sub-Gaussian additive noise. Our maximal concentration inequalities state that the convergence error has a sub-Gaussian tail in the additive noise setting and a Weibull tail (which is faster than polynomial decay but could be slower than exponential decay) in the multiplicative noise setting. In addition, we provide an impossibility result showing that it is generally impossible to have sub-exponential tails under multiplicative noise. To establish the maximal concentration bounds, we develop a novel bootstrapping argument that involves bounding the moment-generating function of a modified version of the generalized Moreau envelope of the convergence error and constructing an exponential supermartingale to enable using Ville's maximal inequality. We demonstrate the applicability of our theoretical results in the context of linear SA and reinforcement learning.

📄 PDF Abstract BibTeX arXiv:2303.15740

Code (0)

등록된 구현이 없습니다.

Tasks

Q-Learning

Similar Papers 제목 키워드 기반

Concentration of Contractive Stochastic Approximation and Reinforcement Learning

2021-06-27 · Siddharth Chandak, Vivek S. Borkar, Parth Dodhia

Using a martingale concentration inequality, concentration bounds `from time $n_0$ on' are derived for stochastic approximation algorithms with contractive maps and both martingale difference and Markov noises. These are…

Q-Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Prelimit Coupling and Steady-State Convergence of Constant-stepsize Nonsmooth Contractive SA

2024-04-09 · Yixuan Zhang, Dongyan Huo, Yudong Chen, Qiaomin Xie

Motivated by Q-learning, we study nonsmooth contractive stochastic approximation (SA) with constant stepsize. We focus on two important classes of dynamics: 1) nonsmooth contractive SA with additive noise, and 2) synchro…

Q-Learning

A General-Purpose Theorem for High-Probability Bounds of Stochastic Approximation with Polyak Averaging

2025-05-27 · Sajad Khodadadian, Martin Zubeldia

Polyak-Ruppert averaging is a widely used technique to achieve the optimal asymptotic variance of stochastic approximation (SA) algorithms, yet its high-probability performance guarantees remain underexplored in general …

Q-Learning

Almost Sure Convergence Rates and Concentration of Stochastic Approximation and Reinforcement Learning with Markovian Noise

2024-11-20 · Xiaochi Qian, Zixuan Xie, Xinyu Liu, Shangtong Zhang

This paper establishes the first almost sure convergence rate and the first maximal concentration bound with exponential tails for general contractive stochastic approximation algorithms with Markovian noise. As a coroll…

Q-Learning

A Concentration Bound for TD(0) with Function Approximation

2023-12-16 · Siddharth Chandak, Vivek S. Borkar

We derive a concentration bound of the type `for all $n \geq n_0$ for some $n_0$' for TD(0) with linear function approximation. We work with online TD learning with samples from a single sample path of the underlying Mar…