English
Related papers

Related papers: On Gaussian approximation for entropy-regularized …

200 papers

Q-learning is widely used algorithm in reinforcement learning community. Under the lookup table setting, its convergence is well established. However, its behavior is known to be unstable with the linear function approximation case. This…

Machine Learning · Computer Science 2025-02-11 Han-Dong Lim , Donghwan Lee

We study Q-learning with Polyak-Ruppert averaging in a discounted Markov decision process in synchronous and tabular settings. Under a Lipschitz condition, we establish a functional central limit theorem for the averaged iteration…

Machine Learning · Statistics 2023-02-21 Xiang Li , Wenhao Yang , Jiadong Liang , Zhihua Zhang , Michael I. Jordan

In this paper we derive non-asymptotic Berry-Esseen bounds for Polyak-Ruppert averaged iterates of the Linear Stochastic Approximation (LSA) algorithm driven by the Markovian noise. Our analysis yields $\mathcal{O}(n^{-1/4})$ convergence…

Machine Learning · Statistics 2025-05-27 Sergey Samsonov , Marina Sheshukova , Eric Moulines , Alexey Naumov

We study the finite-time convergence of projected linear two-time-scale stochastic approximation with constant step sizes and Polyak--Ruppert averaging. We establish an explicit mean-square error bound, decomposing it into two interpretable…

Systems and Control · Electrical Eng. & Systems 2026-04-02 Yitao Bai , Thinh T. Doan , Justin Romberg

Natural policy gradient (NPG) methods with entropy regularization achieve impressive empirical success in reinforcement learning problems with large state-action spaces. However, their convergence properties and the impact of entropy…

Machine Learning · Computer Science 2026-02-17 Semih Cayci , Niao He , R. Srikant

In this paper, a Gauss-Newton Temporal Difference (GNTD) learning method is proposed to solve the Q-learning problem with nonlinear function approximation. In each iteration, our method takes one Gauss-Newton (GN) step to optimize a variant…

Optimization and Control · Mathematics 2024-04-02 Zhifa Ke , Junyu Zhang , Zaiwen Wen

This work presents the first finite-time analysis for the last-iterate convergence of average-reward $Q$-learning with an asynchronous implementation. A key feature of the algorithm we study is the use of adaptive stepsizes, which serve as…

Machine Learning · Computer Science 2026-04-07 Zaiwei Chen , Phalguni Nanda

We study the rate of convergence of linear two-time-scale stochastic approximation methods. We consider two-time-scale linear iterations driven by i.i.d. noise, prove some results on their asymptotic covariance and establish asymptotic…

Probability · Mathematics 2009-09-29 Vijay R. Konda , John N. Tsitsiklis

The proximal gradient algorithm for minimizing the sum of a smooth and a nonsmooth convex function often converges linearly even without strong convexity. One common reason is that a multiple of the step length at each iteration may…

Optimization and Control · Mathematics 2016-06-29 Dmitriy Drusvyatskiy , Adrian S. Lewis

Greedy-GQ with linear function approximation, originally proposed in \cite{maei2010toward}, is a value-based off-policy algorithm for optimal control in reinforcement learning, and it has a non-linear two timescale structure with the…

Machine Learning · Computer Science 2024-05-03 Yue Wang , Yi Zhou , Shaofeng Zou

This paper investigates the approximation of Gaussian random variables in Banach spaces, focusing on the high-probability bounds for the approximation of Gaussian random variables using finitely many observations. We derive non-asymptotic…

Statistics Theory · Mathematics 2025-08-28 Daniel Winkle , Ingo Steinwart , Bernard Haasdonk

We study reinforcement learning methods with linear function approximation under non-Markov state and cost processes. We first consider the policy evaluation method and show that the algorithm converges under suitable ergodicity conditions…

Machine Learning · Computer Science 2026-01-05 Ali Devran Kara

In this paper, we study the quantitative convergence of shallow neural networks trained via gradient descent to their associated Gaussian processes in the infinite-width limit. While previous work has established qualitative convergence…

Machine Learning · Statistics 2026-03-06 Eloy Mosig , Andrea Agazzi , Dario Trevisan

We present simple, user-friendly bounds for the expected operator norm of a random kernel matrix under general conditions on the kernel function $k(\cdot,\cdot)$. Our approach uses decoupling results for U-statistics and the non-commutative…

Machine Learning · Statistics 2025-11-07 Chiraag Kaushik , Justin Romberg , Vidya Muthukumar

This paper presents a novel systematic methodology to obtain new simple and tight approximations, lower bounds, and upper bounds for the Gaussian Q-function, and functions thereof, in the form of a weighted sum of exponential functions.…

Signal Processing · Electrical Eng. & Systems 2020-12-21 Islam M. Tanash , Taneli Riihonen

Q-learning with neural network function approximation (neural Q-learning for short) is among the most prevalent deep reinforcement learning algorithms. Despite its empirical success, the non-asymptotic convergence rate of neural Q-learning…

Machine Learning · Computer Science 2020-03-05 Pan Xu , Quanquan Gu

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…

Machine Learning · Statistics 2023-03-30 Alain Durmus , Eric Moulines , Alexey Naumov , Sergey Samsonov

In this paper, we give a quadratic Goldreich-Levin algorithm that is close to optimal in the following ways. Given a bounded function $f$ on the Boolean hypercube $\mathbb{F}_2^n$ and any $\varepsilon>0$, the algorithm returns a quadratic…

Computational Complexity · Computer Science 2025-05-20 Jop Briët , Davi Castro-Silva

This paper studies function approximation in Gaussian Sobolev spaces over the real line and measures the error in a Gaussian-weighted $L^p$-norm. We construct two linear approximation algorithms using $n$ function evaluations that achieve…

Numerical Analysis · Mathematics 2026-03-20 Yuya Suzuki , Toni Karvonen

Stochastic approximation is a foundation for many algorithms found in machine learning and optimization. It is in general slow to converge: the mean square error vanishes as $O(n^{-1})$. A deterministic counterpart known as quasi-stochastic…

Optimization and Control · Mathematics 2024-03-26 Caio Kalil Lauand , Sean Meyn