中文
相关论文

相关论文: Computing the Bias of Constant-step Stochastic App…

200 篇论文

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…

机器学习 · 计算机科学 2017-09-14 Chandrashekar Lakshminarayanan , Csaba Szepesvári

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…

动力系统 · 数学 2019-02-22 Prasenjit Karmakar , Shalabh Bhatnagar

This paper considers time-average stochastic optimization, where a time average decision vector, an average of decision vectors chosen in every time step from a time-varying (possibly non-convex) set, minimizes a convex objective function…

最优化与控制 · 数学 2015-01-29 Sucha Supittayapornpong , Michael J. Neely

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…

机器学习 · 计算机科学 2020-12-03 Prasenjit Karmakar

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

Stochastic approximation is a framework unifying many random iterative algorithms occurring in a diverse range of applications. The stability of the process is often difficult to verify in practical applications and the process may even be…

概率论 · 数学 2014-03-10 Christophe Andrieu , Matti Vihola

Multi-time-scale stochastic approximation is an iterative algorithm for finding the fixed point of a set of $N$ coupled operators given their noisy samples. It has been observed that due to the coupling between the decision variables and…

最优化与控制 · 数学 2024-09-13 Sihan Zeng , Thinh T. Doan

The ODE method has been a workhorse for algorithm design and analysis since the introduction of the stochastic approximation. It is now understood that convergence theory amounts to establishing robustness of Euler approximations for ODEs,…

最优化与控制 · 数学 2020-10-02 Shuhang Chen , Adithya Devraj , Andrey Bernstein , Sean Meyn

Two-time-scale stochastic approximation (SA) is an algorithm with coupled iterations which has found broad applications in reinforcement learning, optimization and game control. In this work, we derive mean squared error bounds for…

机器学习 · 计算机科学 2026-02-24 Siddharth Chandak

This paper considers a novel multi-agent linear stochastic approximation algorithm driven by Markovian noise and general consensus-type interaction, in which each agent evolves according to its local stochastic approximation process which…

机器学习 · 计算机科学 2023-10-02 Yixuan Lin , Vijay Gupta , Ji Liu

We consider stochastic algorithms derived from methods for solving deterministic optimization problems, especially comparison-based algorithms derived from stochastic approximation algorithms with a constant step-size. We develop a…

最优化与控制 · 数学 2022-01-03 Youhei Akimoto , Anne Auger , Nikolaus Hansen

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 a probabilistic model for stochastic iterative algorithms with the use case of optimization algorithms in mind. Based on this model, we present PAC-Bayesian generalization bounds for functions that are defined on the trajectory…

机器学习 · 计算机科学 2024-08-22 Michael Sucker , Peter Ochs

We study stochastic approximation procedures for approximately solving a $d$-dimensional linear fixed point equation based on observing a trajectory of length $n$ from an ergodic Markov chain. We first exhibit a non-asymptotic bound of the…

最优化与控制 · 数学 2024-05-14 Wenlong Mou , Ashwin Pananjady , Martin J. Wainwright , Peter L. Bartlett

We study momentum-based first-order optimization algorithms in which the iterations utilize information from the two previous steps and are subject to an additive white noise. This setup uses noise to account for uncertainty in either…

最优化与控制 · 数学 2024-06-21 Hesameddin Mohammadi , Meisam Razaviyayn , Mihailo R. Jovanović

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

This paper provides a finite-time analysis of linear stochastic approximation (LSA) algorithms with fixed step size, a core method in statistics and machine learning. LSA is used to compute approximate solutions of a $d$-dimensional linear…

机器学习 · 统计学 2023-03-30 Alain Durmus , Eric Moulines , Alexey Naumov , Sergey Samsonov

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…

最优化与控制 · 数学 2020-03-18 Jingyi Zhu

We consider stochastic variational inequalities with monotone operators defined as the expected value of a random operator. We assume the feasible set is the intersection of a large family of convex sets. We propose a method that combines…

最优化与控制 · 数学 2017-03-03 Alfredo Iusem , Alejandro Jofré , Philip Thompson

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