Statistical Inference for Online Decision Making via Stochastic Gradient Descent

DOI10.1080/01621459.2020.1826325zbMath1465.62032arXiv2010.07341OpenAlexW3098732027MaRDI QIDQ4999148

Rui Song, Haoyu Chen, Wen-Bin Lu

Publication date: 6 July 2021

Published in: Journal of the American Statistical Association (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2010.07341

zbMATH Keywords

value functionbig dataoptimal decision ruleinverse probability weighted estimationonline decision makingepsilon-greedy

Mathematics Subject Classification ID

Minimax procedures in statistical decision theory (62C20) Sequential statistical analysis (62L10) Online algorithms; streaming algorithms (68W27) Statistical aspects of big data and data science (62R07)

Related Items

Online Bootstrap Inference For Policy Evaluation In Reinforcement Learning

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Statistical inference for the mean outcome under a possibly non-unique optimal treatment strategy
• Targeted sequential design for targeted learning inference of the optimal treatment rule and its mean reward
• Fast learning rates for plug-in classifiers
• Randomized allocation with nonparametric estimation for a multi-armed bandit problem with covariates
• Statistical inference for model parameters in stochastic gradient descent
• A One-Armed Bandit Problem with a Concomitant Variable
• Acceleration of Stochastic Approximation by Averaging
• 10.1162/153244303321897663
• A Robust Method for Estimating Optimal Treatment Regimes
• A linear response bandit problem
• Some aspects of the sequential design of experiments
• A Stochastic Approximation Method