English
Related papers

Related papers: Finite-Time Analysis and Restarting Scheme for Lin…

200 papers

We study a new two-time-scale stochastic gradient method for solving optimization problems, where the gradients are computed with the aid of an auxiliary variable under samples generated by time-varying MDPs controlled by the underlying…

Optimization and Control · Mathematics 2024-08-27 Sihan Zeng , Thinh T. Doan , Justin Romberg

Policy evaluation in reinforcement learning is often conducted using two-timescale stochastic approximation, which results in various gradient temporal difference methods such as GTD(0), GTD2, and TDC. Here, we provide convergence rate…

Machine Learning · Computer Science 2019-12-05 Gal Dalal , Balazs Szorenyi , Gugan Thoppe

This paper concerns the convergence of an iterative scheme for 2D stochastic primitive equations on a bounded domain. The stochastic system is split into two equations: a deterministic 2D primitive equations with random initial value and a…

Probability · Mathematics 2019-07-09 Xuhui Peng , Rangrang Zhang

We present for the first time an asymptotic convergence analysis of two time-scale stochastic approximation driven by "controlled" Markov noise. In particular, the faster and slower recursions have non-additive controlled Markov noise…

Machine Learning · Computer Science 2020-12-03 Prasenjit Karmakar

The Expectation-Maximization (EM) algorithm is a popular choice for learning latent variable models. Variants of the EM have been initially introduced, using incremental updates to scale to large datasets, and using Monte Carlo (MC)…

Machine Learning · Statistics 2022-03-22 Belhal Karimi , Ping Li

We study stochastic approximation algorithms with Markovian noise and constant step-size $\alpha$. We develop a method based on infinitesimal generator comparisons to study the bias of the algorithm, which is the expected difference between…

Machine Learning · Statistics 2024-10-28 Sebastian Allmeier , Nicolas Gast

We present adaptive sequential SAA (sample average approximation) algorithms to solve large-scale two-stage stochastic linear programs. The iterative algorithm framework we propose is organized into \emph{outer} and \emph{inner} iterations…

Optimization and Control · Mathematics 2020-12-08 Raghu Pasupathy , Yongjia Song

In this paper, we design, analyze, and implement a variant of the two-loop L-shaped algorithms for solving two-stage stochastic programming problems that arise from important application areas including revenue management and power systems.…

Optimization and Control · Mathematics 2023-09-06 John R. Birge , Haihao Lu , Baoyu Zhou

We consider $d$-dimensional linear stochastic approximation algorithms (LSAs) with a constant step-size and the so called Polyak-Ruppert (PR) averaging of iterates. LSAs are widely applied in machine learning and reinforcement learning…

Machine Learning · Computer Science 2017-09-14 Chandrashekar Lakshminarayanan , Csaba Szepesvári

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

The performance of standard stochastic approximation implementations can vary significantly based on the choice of the steplength sequence, and in general, little guidance is provided about good choices. Motivated by this gap, in the first…

Optimization and Control · Mathematics 2015-03-19 Farzad Yousefian , Angelia Nedić , Uday V. Shanbhag

Motivated by the widespread use of temporal-difference (TD-) and Q-learning algorithms in reinforcement learning, this paper studies a class of biased stochastic approximation (SA) procedures under a mild "ergodic-like" assumption on the…

Machine Learning · Statistics 2020-09-02 Gang Wang , Bingcong Li , Georgios B. Giannakis

Computational multi-scale methods capitalize on a large time-scale separation to efficiently simulate slow dynamics over long time intervals. For stochastic systems, one often aims at resolving the statistics of the slowest dynamics. This…

Numerical Analysis · Mathematics 2021-05-14 Kristian Debrabant , Giovanni Samaey , Przemysław Zieliński

Sequential scaling is a prominent inference-time scaling paradigm, yet its performance improvements are typically modest and not well understood, largely due to the prevalence of heuristic, non-principled approaches that obscure clear…

Machine Learning · Computer Science 2026-02-03 Youkang Wang , Jian Wang , Rubing Chen , Tianyi Zeng , Xiao-Yong Wei , Qing Li

Two time scale stochastic approximation algorithms emulate singularly perturbed deterministic differential equations in a certain limiting sense, i.e., the interpolated iterates on each time scale approach certain differential equations in…

Probability · Mathematics 2023-06-12 Fathima Zarin Faizal , Vivek Borkar

We propose adaptive, line search-free second-order methods with optimal rate of convergence for solving convex-concave min-max problems. By means of an adaptive step size, our algorithms feature a simple update rule that requires solving…

Optimization and Control · Mathematics 2024-11-12 Ruichen Jiang , Ali Kavis , Qiujiang Jin , Sujay Sanghavi , Aryan Mokhtari

We provide performance guarantees for a variant of simulation-based policy iteration for controlling Markov decision processes that involves the use of stochastic approximation algorithms along with state-of-the-art techniques that are…

Machine Learning · Computer Science 2022-10-17 Anna Winnicki , R. Srikant

Greedy-GQ is an off-policy two timescale algorithm for optimal control in reinforcement learning. This paper develops the first finite-sample analysis for the Greedy-GQ algorithm with linear function approximation under Markovian noise. Our…

Machine Learning · Computer Science 2020-05-21 Yue Wang , Shaofeng Zou

In this work we present a new simple but efficient scheme - Subsquares approach - for development of algorithms for enclosing the solution set of overdetermined interval linear systems. We are going to show two algorithms based on this…

Numerical Analysis · Computer Science 2013-05-07 Jaroslav Horáček , Milan Hladík

We present a two-stage least-squares method to inverse medium problems of reconstructing multiple unknown coefficients simultaneously from noisy data. A direct sampling method is applied to detect the location of the inhomogeneity in the…

Numerical Analysis · Mathematics 2022-01-04 Kazufumi Ito , Ying Liang , Jun Zou