Batched bandit problems

DOI10.1214/15-AOS1381zbMath1338.62180arXiv1505.00369MaRDI QIDQ282463

Sylvain Chassang, Erik Snowberg, Vianney Perchet, Philippe Rigollet

Publication date: 12 May 2016

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1505.00369

zbMATH Keywords

sample size determination; batches; grouped clinical trials; multi-armed bandit problems; multi-phase allocation; regret bounds; switching cost

Mathematics Subject Classification ID

62P10: Applications of statistics to biology and medical sciences; meta analysis

62C20: Minimax procedures in statistical decision theory

62L05: Sequential statistical design

Related Items

Rejoinder, Learning the distribution with largest mean: two bandit frameworks, Unnamed Item, Learning Unknown Service Rates in Queues: A Multiarmed Bandit Approach, Bayesian adaptive bandit-based designs using the Gittins index for multi-armed trials with normally distributed endpoints, Bypassing the Monster: A Faster and Simpler Optimal Algorithm for Contextual Bandits Under Realizability, Functional Sequential Treatment Allocation, Greedy Algorithm Almost Dominates in Smoothed Contextual Bandits, Unnamed Item, Online learning of energy consumption for navigation of electric vehicles, Batched bandit problems, Gaussian two-armed bandit: limiting description, Customization of J. Bather's UCB strategy for a Gaussian multiarmed bandit

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Batched bandit problems
• The multi-armed bandit problem with covariates
• Kullback-Leibler upper confidence bounds for optimal sequential allocation
• UCB revisited: improved regret bounds for the stochastic multi-armed bandit problem
• Asymptotically efficient adaptive allocation rules
• Optimal few-stage designs
• Sequential experimentation in clinical trials. Design and analysis
• Multistage bandit problems
• Asymptotically optimal multistage tests of simple hypotheses
• Regret Minimization for Reserve Prices in Second-Price Auctions
• A Sequential Design for the Two Armed Bandit
• An Asymptotic Minimax Theorem for the Two Armed Bandit Problem
• A Learning Approach for Interactive Marketing to a Customer Segment
• Some Remarks on the Two-Armed Bandit
• On the Non-Existence of Tests of "Student's" Hypothesis Having Power Functions Independent of $\sigma$
• Some aspects of the sequential design of experiments
• TWO-STAGE PROCEDURES FOR ESTIMATING THE DIFFERENCE BETWEEN MEANS
• SOME PROBLEMS OF OPTIMUM SAMPLING
• A Two-Sample Test for a Linear Hypothesis Whose Power is Independent of the Variance
• Introduction to nonparametric estimation
• Finite-time analysis of the multiarmed bandit problem