Probabilistic Bisection Converges Almost as Quickly as Stochastic Approximation

• 成果类型: Article
• 署名作者: Frazier, Peter, I; Henderson, Shane G.; Waeber, Rolf
• 署名单位: Cornell University
• 刊物名称: MATHEMATICS OF OPERATIONS RESEARCH
• ISSN/ISSBN: 0364-765X
• DOI: 10.1287/moor.2018.0938
• 发表日期: 2019
• 页码: 651-667
• 关键词: expected sample-size; 20 questions

摘要

The probabilistic bisection algorithm (PBA) solves a class of stochastic root-finding problems in one dimension by successively updating a prior belief on the location of the root based on noisy responses to queries at chosen points. The responses indicate the direction of the root from the queried point and are incorrect with a fixed probability. The fixed-probability assumption is problematic in applications, and so we extend the PBA to apply when this assumption is relaxed. The extension involves the use of a power-one test at each queried point. We explore the convergence behavior of the extended PBA, showing that it converges at a rate arbitrarily close to, but slower than, the canonical square root rate of stochastic approximation.