Boundary crossing probabilities for general exponential families

DOI10.3103/S1066530718010015zbMath1395.62248arXiv1705.08814WikidataQ115488668 ScholiaQ115488668MaRDI QIDQ722599

Odalric-Ambrym Maillard

Publication date: 27 July 2018

Published in: Mathematical Methods of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1705.08814

zbMATH Keywords

exponential familiesoptimalitymulti-armed banditsBregman concentration

Mathematics Subject Classification ID

Stopping times; optimal stopping problems; gambling theory (60G40) Sequential statistical analysis (62L10) Sequential estimation (62L12)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Kullback-Leibler upper confidence bounds for optimal sequential allocation
• Exploration-exploitation tradeoff using variance estimates in multi-armed bandits
• Asymptotically efficient adaptive allocation rules
• Boundary crossing problems for sample means
• Adaptive treatment allocation and the multi-armed bandit problem
• Dominant measures and Sanov's theorem
• Optimal Adaptive Policies for Markov Decision Processes
• Sample mean based index policies by O(log n) regret for the multi-armed bandit problem
• Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems
• On a Criterion for the Rejection of Observations and the Distribution of the Ratio of Deviation to Sample Standard Deviation
• Some aspects of the sequential design of experiments
• Sequential Tests of Statistical Hypotheses
• Finite-time analysis of the multiarmed bandit problem