paper-with-me

Papers

Asymptotic Time-Uniform Inference for Parameters in Averaged Stochastic Approximation

2024-10-19 · Chuhan Xie, Kaicheng Jin, Jiadong Liang, Zhihua Zhang

We study time-uniform statistical inference for parameters in stochastic approximation (SA), which encompasses a bunch of applications in optimization and machine learning. To that end, we analyze the almost-sure convergence rates of the averaged iterates to a scaled sum of Gaussians in both linear and nonlinear SA problems. We then construct three types of asymptotic confidence sequences that are valid uniformly across all times with coverage guarantees, in an asymptotic sense that the starting time is sufficiently large. These coverage guarantees remain valid if the unknown covariance matrix is replaced by its plug-in estimator, and we conduct experiments to validate our methodology.

📄 PDF Abstract BibTeX arXiv:2410.15057

Code (0)

등록된 구현이 없습니다.

Tasks

valid

Similar Papers 제목 키워드 기반

Asymptotic Analysis of Sample-averaged Q-learning

2024-10-14 · Saunak Kumar Panda, Ruiqi Liu, Yisha Xiang

Reinforcement learning (RL) has emerged as a key approach for training agents in complex and uncertain environments. Incorporating statistical inference in RL algorithms is essential for understanding and managing uncert…

OpenAI GymQ-LearningReinforcement Learning (RL)Scheduling

Uniform Inference in High-Dimensional Threshold Regression Models

2024-04-11 · Jiatong Li, Hongqiang Yan

We develop uniform inference for high-dimensional threshold regression parameters, allowing for either cross-sectional or time series data. We first establish Oracle inequalities for prediction errors and $\ell_1$ estima…

regressionTime Seriesvalid

Time-uniform central limit theory and asymptotic confidence sequences

2021-03-11 · Ian Waudby-Smith, David Arbour, Ritwik Sinha, Edward H. Kennedy 외

Confidence intervals based on the central limit theorem (CLT) are a cornerstone of classical statistics. Despite being only asymptotically valid, they are ubiquitous because they permit statistical inference under weak a…

Causal Inferencevalid

Finite-time High-probability Bounds for Polyak-Ruppert Averaged Iterates of Linear Stochastic Approximation

2022-07-10 · Alain Durmus, Eric Moulines, Alexey Naumov, Sergey Samsonov

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 $d$…

Acceleration of stochastic gradient descent with momentum by averaging: finite-sample rates and asymptotic normality

2023-05-28 · Kejie Tang, Weidong Liu, Yichen Zhang, Xi Chen

Stochastic gradient descent with momentum (SGDM) has been widely used in many machine learning and statistical applications. Despite the observed empirical benefits of SGDM over traditional SGD, the theoretical understan…

Uncertainty Quantification