English
Related papers

Related papers: Finite-Time Analysis of Projected Two-Time-Scale S…

200 papers

We study two time-scale linear stochastic approximation algorithms, which can be used to model well-known reinforcement learning algorithms such as GTD, GTD2, and TDC. We present finite-time performance bounds for the case where the…

Machine Learning · Computer Science 2019-07-16 Harsh Gupta , R. Srikant , Lei Ying

We study the finite-time behaviour of the popular temporal difference (TD) learning algorithm when combined with tail-averaging. We derive finite time bounds on the parameter error of the tail-averaged TD iterate under a step-size choice…

Machine Learning · Computer Science 2024-09-20 Gandharv Patil , Prashanth L. A. , Dheeraj Nagaraj , Doina Precup

Two-time-scale optimization is a framework introduced in Zeng et al. (2024) that abstracts a range of policy evaluation and policy optimization problems in reinforcement learning (RL). Akin to bi-level optimization under a particular type…

Optimization and Control · Mathematics 2026-01-21 Sihan Zeng , Thinh T. Doan

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

This work analyzes the stochastic approximation algorithm with non-decaying gains as applied in time-varying problems. The setting is to minimize a sequence of scalar-valued loss functions $f_k(\cdot)$ at sampling times $\tau_k$ or to…

Optimization and Control · Mathematics 2020-03-18 Jingyi Zhu

We define a stochastic variant of the proximal point algorithm in the general setting of nonlinear (separable) Hadamard spaces for approximating zeros of the mean of a stochastically perturbed monotone vector field and prove its convergence…

Optimization and Control · Mathematics 2025-10-14 Nicholas Pischke

In this paper, we analyze the two time-scale stochastic approximation (TTSSA) algorithm introduced in Borkar (1997) using a martingale approach. This approach leads to simple sufficient conditions for the iterations to be bounded almost…

Machine Learning · Statistics 2026-03-17 Mathukumalli Vidyasagar

We consider an incremental approximation method for solving variational problems in infinite-dimensional Hilbert spaces, where in each step a randomly and independently selected subproblem from an infinite collection of subproblems is…

Numerical Analysis · Mathematics 2018-03-06 Michael Griebel , Peter Oswald

We study weighted Tikhonov regularization for large-scale linear discrete ill-posed problems with random noise. Under a polynomial upper-bound assumption on the generalized eigenvalues of the discrete forward operator, we derive stochastic…

Numerical Analysis · Mathematics 2026-05-19 Duan-Peng Ling , Wenlong Zhang

Stochastic Approximation (SA) is a popular approach for solving fixed-point equations where the information is corrupted by noise. In this paper, we consider an SA involving a contraction mapping with respect to an arbitrary norm, and show…

Machine Learning · Computer Science 2021-07-01 Zaiwei Chen , Siva Theja Maguluri , Sanjay Shakkottai , Karthikeyan Shanmugam

We introduce a comprehensive framework for analyzing convergence rates for infinite dimensional linear programming problems (LPs) within the context of the moment-sum-of-squares hierarchy. Our primary focus is on extending the existing…

Optimization and Control · Mathematics 2025-05-09 Corbinian Schlosser , Matteo Tacchi , Alexey Lazarev

We propose a stochastic approximation method for approximating the efficient frontier of chance-constrained nonlinear programs. Our approach is based on a bi-objective viewpoint of chance-constrained programs that seeks solutions on the…

Optimization and Control · Mathematics 2020-05-29 Rohit Kannan , James Luedtke

Smolyak's method, also known as hyperbolic cross approximation or sparse grid method, is a powerful tool to tackle multivariate tensor product problems solely with the help of efficient algorithms for the corresponding univariate problem.…

Numerical Analysis · Mathematics 2021-09-21 Michael Gnewuch , Marcin Wnuk

We consider systems of stochastic evolutionary equations of the $p$-Laplace type. We establish convergence rates for a finite-element based space-time approximation, where the error is measured in a suitable quasi-norm. Under natural…

Analysis of PDEs · Mathematics 2021-05-10 Dominic Breit , Martina Hofmanova , Sebastien Loisel

We study the stochastic $p$-Laplace system in a bounded domain. We propose two new space-time discretizations based on the approximation of time-averaged values. We establish linear convergence in space and $1/2$ convergence in time.…

Numerical Analysis · Mathematics 2023-05-19 Lars Diening , Martina Hofmanová , Jörn Wichmann

We deal with the problem of the mean square optimal estimation of linear transformations of the unobserved values of a continuous time stochastic process with periodically correlated increments. Estimates are based on observations of the…

Statistics Theory · Mathematics 2024-02-12 Maksym Luz , Mikhail Moklyachuk

We consider a class of stochastic gradient optimization schemes. Assuming that the objective function is strongly convex, we prove weak error estimates which are uniform in time for the error between the solution of the numerical scheme,…

Numerical Analysis · Mathematics 2026-01-27 Charles-Edouard Bréhier , Marc Dambrine , Nassim En-Nebbazi

We consider a stochastic version of the proximal point algorithm for optimization problems posed on a Hilbert space. A typical application of this is supervised learning. While the method is not new, it has not been extensively analyzed in…

Optimization and Control · Mathematics 2021-09-28 Monika Eisenmann , Tony Stillfjord , Måns Williamson

We propose and analyze a variant of the classic Polyak-Ruppert averaging scheme, broadly used in stochastic gradient methods. Rather than a uniform average of the iterates, we consider a weighted average, with weights decaying in a…

Machine Learning · Computer Science 2018-02-23 Gergely Neu , Lorenzo Rosasco

We consider a distributed multi-agent network system where the goal is to minimize a sum of convex objective functions of the agents subject to a common convex constraint set. Each agent maintains an iterate sequence and communicates the…

Optimization and Control · Mathematics 2008-11-18 S. Sundhar Ram , A. Nedich , V. V. Veeravalli