English
Related papers

Related papers: A General-Purpose Theorem for High-Probability Bou…

200 papers

Theory and application of stochastic approximation (SA) have become increasingly relevant due in part to applications in optimization and reinforcement learning. This paper takes a new look at SA with constant step-size $\alpha>0$, defined…

Statistics Theory · Mathematics 2025-11-12 Caio Kalil Lauand , Ioannis Kontoyiannis , Sean Meyn

The superiority of symplectic methods for stochastic Hamiltonian systems has been widely recognized, yet the probabilistic mechanism behind this superiority remains incompletely understood. This paper studies the superiority of symplectic…

Numerical Analysis · Mathematics 2025-05-29 Jialin Hong , Ge Liang , Derui Sheng

First-order methods underpin most large-scale learning algorithms, yet their classical convergence guarantees hinge on carefully scheduled step-sizes that depend on the total horizon $T$, which is rarely known in advance. The Schedule-Free…

Machine Learning · Computer Science 2025-08-12 Connor Brown

Recently, the stochastic asymptotical regularization (SAR) has been developed in (\emph{Inverse Problems}, 39: 015007, 2023) for the uncertainty quantification of the stable approximate solution of linear ill-posed inverse problems. In this…

Numerical Analysis · Mathematics 2024-08-27 Haie Long , Ye Zhang

We study Q-learning with Polyak-Ruppert averaging in a discounted Markov decision process in synchronous and tabular settings. Under a Lipschitz condition, we establish a functional central limit theorem for the averaged iteration…

Machine Learning · Statistics 2023-02-21 Xiang Li , Wenhao Yang , Jiadong Liang , Zhihua Zhang , Michael I. Jordan

Two-timescale Stochastic Approximation (SA) algorithms are widely used in Reinforcement Learning (RL). Their iterates have two parts that are updated using distinct stepsizes. In this work, we develop a novel recipe for their finite sample…

Artificial Intelligence · Computer Science 2018-06-06 Gal Dalal , Balazs Szorenyi , Gugan Thoppe , Shie Mannor

The Metropolis process (MP) and Simulated Annealing (SA) are stochastic local search heuristics that are often used in solving combinatorial optimization problems. Despite significant interest, there are very few theoretical results…

Data Structures and Algorithms · Computer Science 2023-12-22 Zongchen Chen , Dan Mikulincer , Daniel Reichman , Alexander S. Wein

This paper develops several average-case reduction techniques to show new hardness results for three central high-dimensional statistics problems, implying a statistical-computational gap induced by robustness, a detection-recovery gap and…

Computational Complexity · Computer Science 2020-05-20 Matthew Brennan , Guy Bresler

Stochastic gradient descent (SGD) for strongly convex functions converges at the rate $\bO(1/k)$. However, achieving good results in practice requires tuning the parameters (for example the learning rate) of the algorithm. In this paper we…

Optimization and Control · Mathematics 2019-07-15 Adam M. Oberman , Mariana Prazeres

We describe methods for proving bounds on infinite-time averages in differential dynamical systems. The methods rely on the construction of nonnegative polynomials with certain properties, similarly to the way nonlinear stability can be…

Dynamical Systems · Mathematics 2021-06-25 David Goluskin

Stochastic approximation is a powerful class of algorithms with celebrated success. However, a large body of previous analysis focuses on stochastic approximations driven by contractive operators, which is not applicable in some important…

Machine Learning · Computer Science 2025-11-21 Ethan Blaser , Shangtong Zhang

We consider applying stochastic approximation (SA) methods to solve nonsmooth variational inclusion problems. Existing studies have shown that the averaged iterates of SA methods exhibit asymptotic normality, with an optimal limiting…

Machine Learning · Statistics 2025-08-13 Liwei Jiang , Abhishek Roy , Krishna Balasubramanian , Damek Davis , Dmitriy Drusvyatskiy , Sen Na

We study the problem of solving fixed-point equations for seminorm-contractive operators and establish foundational results on the non-asymptotic behavior of iterative algorithms in both deterministic and stochastic settings. Specifically,…

Machine Learning · Computer Science 2025-02-21 Zaiwei Chen , Sheng Zhang , Zhe Zhang , Shaan Ul Haque , Siva Theja Maguluri

Two-stage stochastic optimization is a framework for modeling uncertainty, where we have a probability distribution over possible realizations of the data, called scenarios, and decisions are taken in two stages: we make first-stage…

Data Structures and Algorithms · Computer Science 2023-10-25 Andre Linhares , Chaitanya Swamy

We provide non-asymptotic convergence rates of the Polyak-Ruppert averaged stochastic gradient descent (SGD) to a normal random vector for a class of twice-differentiable test functions. A crucial intermediate step is proving a…

Statistics Theory · Mathematics 2019-04-04 Andreas Anastasiou , Krishnakumar Balasubramanian , Murat A. Erdogdu

Constant-stepsize stochastic approximation (SA) is widely used in learning for computational efficiency. For a fixed stepsize, the iterates typically admit a stationary distribution that is rarely tractable. Prior work shows that as the…

Machine Learning · Computer Science 2026-02-17 Zedong Wang , Yuyang Wang , Ijay Narang , Felix Wang , Yuzhou Wang , Siva Theja Maguluri

The popular $\mathcal{AB}$/push-pull method for distributed optimization problem may unify much of the existing decentralized first-order methods based on gradient tracking technique. More recently, the stochastic gradient variant of…

Optimization and Control · Mathematics 2022-09-13 Shengchao Zhao , Yongchao Liu

In this paper, we establish sublinear and linear convergence of fixed point iterations generated by averaged operators in a Hilbert space. Our results are achieved under a bounded H\"older regularity assumption which generalizes the…

Optimization and Control · Mathematics 2018-08-16 Jonathan M. Borwein , Guoyin Li , Matthew K. Tam

Stochastic approximation (SA) with multiple coupled sequences has found broad applications in machine learning such as bilevel learning and reinforcement learning (RL). In this paper, we study the finite-time convergence of nonlinear SA…

Machine Learning · Computer Science 2022-06-22 Han Shen , Tianyi Chen

In this paper, we analyze the finite sample complexity of stochastic system identification using modern tools from machine learning and statistics. An unknown discrete-time linear system evolves over time under Gaussian noise without…

Machine Learning · Computer Science 2019-03-22 Anastasios Tsiamis , George J. Pappas