English
Related papers

Related papers: Gaussian Approximation for Asynchronous Q-learning

200 papers

We describe a general technique that yields the first {\em Statistical Query lower bounds} for a range of fundamental high-dimensional learning problems involving Gaussian distributions. Our main results are for the problems of (1) learning…

Machine Learning · Computer Science 2017-05-18 Ilias Diakonikolas , Daniel M. Kane , Alistair Stewart

We study the convergence rate of randomly truncated stochastic algorithms, which consist in the truncation of the standard Robbins-Monro procedure on an increasing sequence of compact sets. Such a truncation is often required in practice to…

Probability · Mathematics 2010-04-08 Jérôme Lelong

We study the convergence rate of randomly truncated stochastic algorithms, which consist in the truncation of the standard Robbins-Monro procedure on an increasing sequence of compact sets. Such a truncation is often required in practice to…

Probability · Mathematics 2010-03-23 Jérôme Lelong

We provide rates of convergence in the central limit theorem in terms of projective criteria for adapted stationary sequences of centered random variables taking values in Banach spaces, with finite moment of order $p \in ]2,3]$ as soon as…

Probability · Mathematics 2025-02-21 Aurélie Bigot

Q-learning has long been one of the most popular reinforcement learning algorithms, and theoretical analysis of Q-learning has been an active research topic for decades. Although researches on asymptotic convergence analysis of Q-learning…

Artificial Intelligence · Computer Science 2022-07-26 Han-Dong Lim , Donghwan Lee

Average-reward reinforcement learning offers a principled framework for long-term decision-making by maximizing the mean reward per time step. Although Q-learning is a widely used model-free algorithm with established sample complexity in…

Machine Learning · Statistics 2026-01-21 Yuchen Jiao , Jiin Woo , Gen Li , Gauri Joshi , Yuejie Chi

This paper establishes convergence rates for learning elliptic pseudo-differential operators, a fundamental operator class in partial differential equations and mathematical physics. In a wavelet-Galerkin framework, we formulate learning…

Statistics Theory · Mathematics 2026-01-09 Jiaheng Chen , Daniel Sanz-Alonso

We study the common continual learning setup where an overparameterized model is sequentially fitted to a set of jointly realizable tasks. We analyze forgetting, defined as the loss on previously seen tasks, after $k$ iterations. For…

Machine Learning · Computer Science 2026-01-05 Itay Evron , Ran Levinstein , Matan Schliserman , Uri Sherman , Tomer Koren , Daniel Soudry , Nathan Srebro

The paper addresses parametric inequality systems described by polynomial functions in finite dimensions, where state-dependent infinite parameter sets are given by finitely many polynomial inequalities and equalities. Such systems can be…

Optimization and Control · Mathematics 2015-09-15 G. Li , B. S. Mordukhovich , T. T. A. Nghia , T. S. Pham

We study the efficient learnability of high-dimensional Gaussian mixtures in the outlier-robust setting, where a small constant fraction of the data is adversarially corrupted. We resolve the polynomial learnability of this problem when the…

Data Structures and Algorithms · Computer Science 2020-05-14 Ilias Diakonikolas , Samuel B. Hopkins , Daniel Kane , Sushrut Karmalkar

Given data drawn from a mixture of multivariate Gaussians, a basic problem is to accurately estimate the mixture parameters. We give an algorithm for this problem that has a running time, and data requirement polynomial in the dimension and…

Machine Learning · Computer Science 2010-04-27 Ankur Moitra , Gregory Valiant

We develop minimax optimal risk bounds for the general learning task consisting in predicting as well as the best function in a reference set G up to the smallest possible additive term, called the convergence rate. When the reference set…

Statistics Theory · Mathematics 2008-03-04 Jean-Yves Audibert

We provide efficient replicable algorithms for the problem of learning large-margin halfspaces. Our results improve upon the algorithms provided by Impagliazzo, Lei, Pitassi, and Sorrell [STOC, 2022]. We design the first…

Machine Learning · Computer Science 2025-10-15 Alkis Kalavasis , Amin Karbasi , Kasper Green Larsen , Grigoris Velegkas , Felix Zhou

We consider a class of random quantum circuits where at each step a gate from a universal set is applied to a random pair of qubits, and determine how quickly averages of arbitrary finite-degree polynomials in the matrix elements of the…

Quantum Physics · Physics 2015-05-14 Winton G. Brown , Lorenza Viola

In this paper we present a method for learning the parameters of a mixture of $k$ identical spherical Gaussians in $n$-dimensional space with an arbitrarily small separation between the components. Our algorithm is polynomial in all…

Machine Learning · Computer Science 2010-05-14 Mikhail Belkin , Kaushik Sinha

Schedule-Free SGD, proposed in [Defazio et al., 2024], achieves optimal convergence rates without requiring the training horizon in advance, by replacing learning rate schedules with a principled form of iterate averaging. However, the…

Machine Learning · Computer Science 2026-05-13 Dimitris Oikonomou , Matthew Buchholz , Yuen-Man Pun , Robert M. Gower , Nicolas Loizou

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

The Zap Q-learning algorithm introduced in this paper is an improvement of Watkins' original algorithm and recent competitors in several respects. It is a matrix-gain algorithm designed so that its asymptotic variance is optimal. Moreover,…

Systems and Control · Computer Science 2018-03-23 Adithya M. Devraj , Sean P. Meyn

We study the policy evaluation problem in multi-agent reinforcement learning, modeled by a Markov decision process. In this problem, the agents operate in a common environment under a fixed control policy, working together to discover the…

Optimization and Control · Mathematics 2020-01-13 Thinh T. Doan , Siva Theja Maguluri , Justin Romberg

Stochastic gradient algorithms are more and more studied since they can deal efficiently and online with large samples in high dimensional spaces. In this paper, we first establish a Central Limit Theorem for these estimates as well as for…

Statistics Theory · Mathematics 2017-10-17 Antoine Godichon-Baggioni