Practical Nonparametric Sampling Strategies for Quantile-Based Ordinal Optimization

Dongwook Shin, Mark Broadie, Assaf Zeevi

Research output: Contribution to journalArticlepeer-review

Abstract

Given a finite number of stochastic systems, the goal of our problemis to dynamically allocate a finite sampling budget to maximize the probability of selecting the "best"system. Systems are encoded with the probability distributions that govern sample observations, which are unknown and only assumed to belong to a broad family of distributions that need not admit any parametric representation. The best system is defined as the one with the highest quantile value. The objective of maximizing the probability of selecting this best system is not analytically tractable. In lieu of that, we use the rate function for the probability of error relying on large deviations theory. Our point of departure is an algorithmthat naively combines sequential estimation andmyopic optimization. This algorithm is shown to be asymptotically optimal; however, it exhibits poor finite-time performance and does not lead itself to implementation in settings with a large number of systems. To address this, we propose practically implementable variants that retain the asymptotic performance of the former while dramatically improving its finite-time performance.

Original languageEnglish
Pages (from-to)752-768
Number of pages17
JournalINFORMS Journal on Computing
Volume34
Issue number2
DOIs
StatePublished - Mar 2022
Externally publishedYes

Keywords

  • large deviations theory
  • ordinal optimization
  • quantile
  • tractable procedures

Fingerprint

Dive into the research topics of 'Practical Nonparametric Sampling Strategies for Quantile-Based Ordinal Optimization'. Together they form a unique fingerprint.

Cite this