中文
相关论文

相关论文: Central Limit Theorem for Two-Timescale Stochastic…

200 篇论文

Stochastic approximation (SA) is an iterative algorithm for finding the fixed point of an operator using noisy samples and widely used in optimization and Reinforcement Learning (RL). The noise in RL exhibits a Markovian structure, and in…

机器学习 · 计算机科学 2025-05-13 Shaan Ul Haque , Sajad Khodadadian , Siva Theja Maguluri

In this paper, we establish non-asymptotic bounds for accuracy of normal approximation for linear two-timescale stochastic approximation (TTSA) algorithms driven by martingale difference or Markov noise. Focusing on both the last iterate…

机器学习 · 统计学 2025-12-10 Bogdan Butyrin , Artemy Rubtsov , Alexey Naumov , Vladimir Ulyanov , Sergey Samsonov

We consider linear two-time-scale stochastic approximation algorithms driven by martingale noise. Recent applications in machine learning motivate the need to understand finite-time error rates, but conventional stochastic approximation…

机器学习 · 计算机科学 2025-12-12 Seo Taek Kong , Sihan Zeng , Thinh T. Doan , R. Srikant

In this work, we study the asymptotic randomness of an algorithmic estimator of the saddle point of a globally convex-concave and locally strongly-convex strongly-concave objective. Specifically, we show that the averaged iterates of a…

最优化与控制 · 数学 2023-11-07 Abhishek Roy , Yi-An Ma

This paper provides a Central Limit Theorem (CLT) for a process $\{\theta_n, n\geq 0\}$ satisfying a stochastic approximation (SA) equation of the form $\theta_{n+1} = \theta_n + \gamma_{n+1} H(\theta_n,X_{n+1})$; a CLT for the associated…

概率论 · 数学 2013-09-13 Gersende Fort

We consider stochastic approximations of sampling algorithms, such as Stochastic Gradient Langevin Dynamics (SGLD) and the Random Batch Method (RBM) for Interacting Particle Dynamcs (IPD). We observe that the noise introduced by the…

概率论 · 数学 2023-10-10 Aniket Das , Dheeraj Nagaraj , Anant Raj

Linear two-timescale stochastic approximation (SA) scheme is an important class of algorithms which has become popular in reinforcement learning (RL), particularly for the policy evaluation problem. Recently, a number of works have been…

机器学习 · 统计学 2020-02-05 Maxim Kaledin , Eric Moulines , Alexey Naumov , Vladislav Tadic , Hoi-To Wai

We consider probabilistic model checking for continuous-time Markov chains (CTMCs) induced from Stochastic Reaction Networks (SRNs) against a fragment of Continuous Stochastic Logic (CSL) extended with reward operators. Classical numerical…

计算机科学中的逻辑 · 计算机科学 2018-04-25 Luca Bortolussi , Luca Cardelli , Marta Kwiatkowska , Luca Laurenti

We are interested in understanding stability (almost sure boundedness) of stochastic approximation algorithms (SAs) driven by a `controlled Markov' process. Analyzing this class of algorithms is important, since many reinforcement learning…

系统与控制 · 计算机科学 2018-05-18 Arunselvan Ramaswamy , Shalabh Bhatnagar

We develop a central limit theorem (CLT) for a non-parametric estimator of the transition matrices in controlled Markov chains (CMCs) with finite state-action spaces. Our results establish precise conditions on the logging policy under…

统计理论 · 数学 2026-03-26 Ziwei Su , Imon Banerjee , Diego Klabjan

This paper develops asymptotic theory for quantile estimation via stochastic gradient descent (SGD) with a constant learning rate. The quantile loss function is neither smooth nor strongly convex. Beyond conventional perspectives and…

机器学习 · 统计学 2026-04-06 Ziyang Wei , Jiaqi Li , Likai Chen , Wei Biao Wu

This paper presents a finite time convergence analysis for a decentralized stochastic approximation (SA) scheme. The scheme generalizes several algorithms for decentralized machine learning and multi-agent reinforcement learning. Our proof…

最优化与控制 · 数学 2020-11-06 Hoi-To Wai

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…

机器学习 · 统计学 2026-03-17 Mathukumalli Vidyasagar

Motivated by engineering applications such as resource allocation in networks and inventory systems, we consider average-reward Reinforcement Learning with unbounded state space and reward function. Recent works studied this problem in the…

机器学习 · 计算机科学 2025-11-10 Shaan Ul Haque , Siva Theja Maguluri

Two-time-scale Stochastic Approximation (SA) is an iterative algorithm with applications in reinforcement learning and optimization. Prior finite time analysis of such algorithms has focused on fixed point iterations with mappings…

机器学习 · 计算机科学 2025-09-30 Siddharth Chandak , Shaan Ul Haque , Nicholas Bambos

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

动力系统 · 数学 2017-02-28 Prasenjit Karmakar , Shalabh Bhatnagar

The focus of this paper is on stochastic variational inequalities (VI) under Markovian noise. A prominent application of our algorithmic developments is the stochastic policy evaluation problem in reinforcement learning. Prior…

最优化与控制 · 数学 2021-08-17 Georgios Kotsalis , Guanghui Lan , Tianjiao Li

Stochastic approximation (SA) is a fundamental iterative framework with broad applications in reinforcement learning and optimization. Classical analyses typically rely on martingale difference or Markov noise with bounded second moments,…

机器学习 · 计算机科学 2026-03-23 Siddharth Chandak , Anuj Yadav , Ayfer Ozgur , Nicholas Bambos

In this paper, we characterize the noise of stochastic gradients and analyze the noise-induced dynamics during training deep neural networks by gradient-based optimizers. Specifically, we firstly show that the stochastic gradient noise…

机器学习 · 计算机科学 2021-09-22 Yixin Wu , Rui Luo , Chen Zhang , Jun Wang , Yaodong Yang

Stochastic gradient descent in continuous time (SGDCT) provides a computationally efficient method for the statistical learning of continuous-time models, which are widely used in science, engineering, and finance. The SGDCT algorithm…

概率论 · 数学 2019-06-18 Justin Sirignano , Konstantinos Spiliopoulos
‹ 上一页 1 2 3 10 下一页 ›