English
Related papers

Related papers: Convergence of Markovian Stochastic Approximation …

200 papers

This paper investigates the stability and convergence properties of asynchronous stochastic approximation (SA) algorithms, with a focus on extensions relevant to average-reward reinforcement learning. We first extend a stability proof…

Machine Learning · Computer Science 2025-12-10 Huizhen Yu , Yi Wan , Richard S. Sutton

Motivated by applications in reinforcement learning (RL), we study a nonlinear stochastic approximation (SA) algorithm under Markovian noise, and establish its finite-sample convergence bounds under various stepsizes. Specifically, we show…

Optimization and Control · Mathematics 2022-01-27 Zaiwei Chen , Sheng Zhang , Thinh T. Doan , John-Paul Clarke , Siva Theja Maguluri

Stochastic gradient descent (SGD) is a popular algorithm for minimizing objective functions that arise in machine learning. For constant step-sized SGD, the iterates form a Markov chain on a general state space. Focusing on a class of…

Optimization and Control · Mathematics 2025-03-26 David Shirokoff , Philip Zaleski

We develop the mathematical foundations of the stochastic modified equations (SME) framework for analyzing the dynamics of stochastic gradient algorithms, where the latter is approximated by a class of stochastic differential equations with…

Machine Learning · Computer Science 2018-11-06 Qianxiao Li , Cheng Tai , Weinan E

Consider a probability measure supported by a regular geodesic ball in a manifold. For any p larger than or equal to 1 we define a stochastic algorithm which converges almost surely to the p-mean of the measure. Assuming furthermore that…

Probability · Mathematics 2011-06-28 Marc Arnaudon , Clément Dombry , Anthony Phan , Le Yang

Stochastic gradient descent type methods are ubiquitous in machine learning, but they are only applicable to the optimization of differentiable functions. Proximal algorithms are more general and applicable to nonsmooth functions. We…

Optimization and Control · Mathematics 2025-05-20 Laurent Condat , Elnur Gasanov , Peter Richtárik

This paper analyzes the trajectories of stochastic gradient descent (SGD) to help understand the algorithm's convergence properties in non-convex problems. We first show that the sequence of iterates generated by SGD remains bounded and…

Optimization and Control · Mathematics 2020-06-22 Panayotis Mertikopoulos , Nadav Hallak , Ali Kavis , Volkan Cevher

In a real Hilbert space setting, we study the convergence properties of an inexact gradient algorithm featuring both viscous and Hessian driven damping for convex differentiable optimization. In this algorithm, the gradient evaluation can…

Optimization and Control · Mathematics 2025-09-25 Harsh Choudhary , Jalal Fadili , Vyachelav Kungurtsev

The purpose of this paper is to establish the almost sure weak ergodic convergence of a sequence of iterates $(x_n)$ given by $x_{n+1} = (I+\lambda_n A(\xi_{n+1},\,.\,))^{-1}(x_n)$ where $(A(s,\,.\,):s\in E)$ is a collection of maximal…

Optimization and Control · Mathematics 2016-07-26 Pascal Bianchi

We consider a Markov chain $(x_n)$ whose kernel is indexed by a scaling parameter $\gamma>0$, refered to as the step size. The aim is to analyze the behavior of the Markov chain in the doubly asymptotic regime where $n\to\infty$ then…

Probability · Mathematics 2017-12-18 Pascal Bianchi , Walid Hachem , Adil Salim

Stochastic non-smooth convex optimization constitutes a class of problems in machine learning and operations research. This paper considers minimization of a non-smooth function based on stochastic subgradients. When the function has a…

Optimization and Control · Mathematics 2016-07-12 Sucha Supittayapornpong , Michael J. Neely

Stochastic approximation is a class of algorithms that update a vector iteratively, incrementally, and stochastically, including, e.g., stochastic gradient descent and temporal difference learning. One fundamental challenge in analyzing a…

Machine Learning · Computer Science 2025-11-06 Shuze Daniel Liu , Shuhang Chen , Shangtong Zhang

This paper compiles several aspects of the dynamics of stochastic approximation algorithms with Markov iterate-dependent noise when the iterates are not known to be stable beforehand. We achieve the same by extending the lock-in probability…

Dynamical Systems · Mathematics 2019-02-22 Prasenjit Karmakar , Shalabh Bhatnagar

We present a finite-time analysis of two smoothed functional stochastic approximation algorithms for simulation-based optimization. The first is a two time-scale gradient-based method, while the second is a three time-scale Newton-based…

Machine Learning · Computer Science 2026-04-01 Kaustubh Kartikey , Shalabh Bhatnagar

We develop a stochastic approximation-type algorithm to solve finite state/action, infinite-horizon, risk-aware Markov decision processes. Our algorithm has two loops. The inner loop computes the risk by solving a stochastic saddle-point…

Optimization and Control · Mathematics 2019-12-05 Wenjie Huang , William B. Haskell

The vast majority of convergence rates analysis for stochastic gradient methods in the literature focus on convergence in expectation, whereas trajectory-wise almost sure convergence is clearly important to ensure that any instantiation of…

Machine Learning · Computer Science 2022-07-12 Jun Liu , Ye Yuan

Gradient-based algorithms are one of the methods of choice for the optimisation of Markov Decision Processes. In this article we will present a novel approximate Newton algorithm for the optimisation of such models. The algorithm has…

Optimization and Control · Mathematics 2015-08-05 Thomas Furmston , David Barber

A stochastic incremental subgradient algorithm for the minimization of a sum of convex functions is introduced. The method sequentially uses partial subgradient information and the sequence of partial subgradients is determined by a general…

Optimization and Control · Mathematics 2021-08-24 Rafael Massambone , Eduardo F. Costa , Elias S. Helou

We propose a novel study of the stochastic proximal gradient method for minimizing the sum of two convex functions, one of which is smooth. Under suitable assumptions and without requiring any boundedness or control of the variance of the…

Optimization and Control · Mathematics 2026-04-16 Javier I. Madariaga

We investigate the Randomized Stochastic Accelerated Gradient (RSAG) method, utilizing either constant or adaptive step sizes, for stochastic optimization problems with generalized smooth objective functions. Under relaxed affine variance…

Optimization and Control · Mathematics 2025-02-25 Chenhao Yu , Yusu Hong , Junhong Lin