paper-with-me

Papers

Improved Central Limit Theorem and Bootstrap Approximations for Linear Stochastic Approximation

2025-10-14 · Bogdan Butyrin, Eric Moulines, Alexey Naumov, Sergey Samsonov, Qi-Man Shao, Zhuo-Song Zhang arxiv

In this paper, we refine the Berry-Esseen bounds for the multivariate normal approximation of Polyak-Ruppert averaged iterates arising from the linear stochastic approximation (LSA) algorithm with decreasing step size. We consider the normal approximation by the Gaussian distribution with covariance matrix predicted by the Polyak-Juditsky central limit theorem and establish the rate up to order $n^{-1/3}$ in convex distance, where $n$ is the number of samples used in the algorithm. We also prove a non-asymptotic validity of the multiplier bootstrap procedure for approximating the distribution of the rescaled error of the averaged LSA estimator. We establish approximation rates of order up to $1/\sqrt{n}$ for the latter distribution, which significantly improves upon the previous results obtained by Samsonov et al. (2024).

📄 PDF Abstract BibTeX arXiv:2510.12375

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Sharp Gaussian approximations for Decentralized Federated Learning

2025-05-12 · Soham Bonnerjee, Sayar Karmakar, Wei Biao Wu

Federated Learning has gained traction in privacy-sensitive collaborative environments, with local SGD emerging as a key optimization method in decentralized settings. While its convergence properties are well-studied, a…

Federated Learningvalid

Limit Theorems for Factor Models

2020-09-23

The paper establishes the central limit theorems and proposes how to perform valid inference in factor models. We consider a setting where many counties/regions/assets are observed for many time periods, and when estimat…

Time SeriesTime Series Analysisvalid

Jointly Exchangeable Collective Risk Models: Interaction, Structure, and Limit Theorems

2025-04-02 · Daniel Gaigall, Stefan Weber

We introduce a framework for systemic risk modeling in insurance portfolios using jointly exchangeable arrays, extending classical collective risk models to account for interactions. We establish central limit theorems t…

A Note on the Prediction-Powered Bootstrap

2024-05-28 · Tijana Zrnic

We introduce PPBoot: a bootstrap-based method for prediction-powered inference. PPBoot is applicable to arbitrary estimation problems and is very simple to implement, essentially only requiring one application of the boo…

Prediction

Gaussian Approximation and Multiplier Bootstrap for Stochastic Gradient Descent

2025-02-10 · Marina Sheshukova, Sergey Samsonov, Denis Belomestny, Eric Moulines 외

In this paper, we establish non-asymptotic convergence rates in the central limit theorem for Polyak-Ruppert-averaged iterates of stochastic gradient descent (SGD). Our analysis builds on the result of the Gaussian appro…