English
Related papers

Related papers: Gaussian Approximation for Asynchronous Q-learning

200 papers

Continual learning, the ability of a model to adapt to an ongoing sequence of tasks without forgetting earlier ones, is a central goal of artificial intelligence. To better understand its underlying mechanisms, we study the limitations of…

Machine Learning · Statistics 2026-04-21 Hossein Taheri , Avishek Ghosh , Arya Mazumdar

Asynchronous parallel implementations of stochastic gradient (SG) have been broadly used in solving deep neural network and received many successes in practice recently. However, existing theories cannot explain their convergence and…

Optimization and Control · Mathematics 2019-04-22 Xiangru Lian , Yijun Huang , Yuncheng Li , Ji Liu

In this paper, we present a framework to understand the convergence of commonly used Q-learning reinforcement learning algorithms in practice. Two salient features of such algorithms are: (i)~the Q-table is recursively updated using an…

Machine Learning · Computer Science 2025-09-04 Amit Sinha , Matthieu Geist , Aditya Mahajan

In scalable machine learning systems, model training is often parallelized over multiple nodes that run without tight synchronization. Most analysis results for the related asynchronous algorithms use an upper bound on the information…

Machine Learning · Computer Science 2022-04-12 Xuyang Wu , Sindri Magnusson , Hamid Reza Feyzmahdavian , Mikael Johansson

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

We give optimal convergence rates in the central limit theorem for a large class of martingale difference sequences with bounded third moments. The rates depend on the behaviour of the conditional variances and for stationary sequences the…

Probability · Mathematics 2007-05-23 Mohamed El Machkouri , Lahcen Ouchti

In this work, we present the first finite-time analysis of Q-learning with time-varying learning policies (i.e., on-policy sampling) for discounted Markov decision processes under minimal assumptions, requiring only the existence of a…

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

In this paper, we establish a Quantitative Central Limit Theorem ({\sc qclt}) for the Stochastic Gradient Descent in Continuous Time ({\sc sgdct}) algorithm, whose parameter updates are governed by a stochastic differential equation. We…

Probability · Mathematics 2026-03-10 Solesne Bourguin , Shivam S. Dhama , Konstantinos Spiliopoulos

We consider a general class of regression models with normally distributed covariates, and the associated nonconvex problem of fitting these models from data. We develop a general recipe for analyzing the convergence of iterative algorithms…

Optimization and Control · Mathematics 2021-09-22 Kabir Aladin Chandrasekher , Ashwin Pananjady , Christos Thrampoulidis

In this paper, we establish sublinear and linear convergence of fixed point iterations generated by averaged operators in a Hilbert space. Our results are achieved under a bounded H\"older regularity assumption which generalizes the…

Optimization and Control · Mathematics 2018-08-16 Jonathan M. Borwein , Guoyin Li , Matthew K. Tam

In this paper, we use tools from rate-distortion theory to establish new upper bounds on the generalization error of statistical distributed learning algorithms. Specifically, there are $K$ clients whose individually chosen models are…

Machine Learning · Statistics 2022-11-23 Milad Sefidgaran , Romain Chor , Abdellatif Zaidi

We study how the learning rate affects the performance of a relaxed randomized Kaczmarz algorithm for solving $A x \approx b + \varepsilon$, where $A x =b$ is a consistent linear system and $\varepsilon$ has independent mean zero random…

Numerical Analysis · Mathematics 2022-08-10 Nicholas F. Marshall , Oscar Mickelin

The $Q$-learning algorithm is a simple and widely-used stochastic approximation scheme for reinforcement learning, but the basic protocol can exhibit instability in conjunction with function approximation. Such instability can be observed…

Machine Learning · Computer Science 2022-06-03 Andrea Zanette , Martin J. Wainwright

In this paper, we study the averaging principle and central limit theorem for multi-scale stochastic differential equations with state-dependent switching. To accomplish this, we first study the Poisson equation associated with a Markov…

Probability · Mathematics 2023-12-19 Xiaobin Sun , Yingchao Xie

When the data used for reinforcement learning (RL) are collected by multiple agents in a distributed manner, federated versions of RL algorithms allow collaborative learning without the need for agents to share their local data. In this…

Machine Learning · Computer Science 2023-12-14 Jiin Woo , Gauri Joshi , Yuejie Chi

Many machine learning and optimization algorithms can be cast as instances of stochastic approximation (SA). The convergence rate of these algorithms is known to be slow, with the optimal mean squared error (MSE) of order $O(n^{-1})$. In…

Optimization and Control · Mathematics 2024-09-13 Caio Kalil Lauand , Sean Meyn

We consider model-free reinforcement learning for infinite-horizon discounted Markov Decision Processes (MDPs) with a continuous state space and unknown transition kernel, when only a single sample path under an arbitrary policy of the…

Machine Learning · Computer Science 2018-10-24 Devavrat Shah , Qiaomin Xie

In this paper we consider the problem of obtaining sharp bounds for the performance of temporal difference (TD) methods with linear function approximation for policy evaluation in discounted Markov decision processes. We show that a simple…

Machine Learning · Statistics 2024-06-18 Sergey Samsonov , Daniil Tiapkin , Alexey Naumov , Eric Moulines

We investigate reinforcement learning in the setting of Markov decision processes for a large number of exchangeable agents interacting in a mean field manner. Applications include, for example, the control of a large number of robots…

Optimization and Control · Mathematics 2025-04-30 René Carmona , Mathieu Laurière , Zongjun Tan

We study the problem of list-decodable Gaussian mean estimation and the related problem of learning mixtures of separated spherical Gaussians. We develop a set of techniques that yield new efficient algorithms with significantly improved…

Data Structures and Algorithms · Computer Science 2017-11-21 Ilias Diakonikolas , Daniel M. Kane , Alistair Stewart