mlsanityData to 7 Oct 2026

Efficient Learning for Selecting Top-m Context-Dependent Designs

arXiv 2305.04086 ↗First posted 6 May 2023stat.ML math.OCcited by 0

Not on the map. Why?

Abstract (arXiv)

We consider a simulation optimization problem for a context-dependent decision-making, which aims to determine the top-m designs for all contexts. Under a Bayesian framework, we formulate the optimal dynamic sampling decision as a stochastic dynamic programming problem, and develop a sequential sampling policy to efficiently learn the performance of each design under each context. The asymptotically optimal sampling ratios are derived to attain the optimal large deviations rate of the worst-case of probability of false selection. The proposed sampling policy is proved to be consistent and its asymptotic sampling ratios are asymptotically optimal. Numerical experiments demonstrate that the proposed method improves the efficiency for selection of top-m context-dependent designs.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 15 of its 63 references that are in the map. First posted on arXiv 6 May 2023.

Builds on

15 of 63 references.

References · 15

  1. 2019Contextual Bandits with Continuous Actions: Smoothing, Zooming, and Adaptingcited by 42
  2. 2017Nearly Instance Optimal Sample Complexity Bounds for Top-k Arm Selectioncited by 28
  3. 2020Review on Ranking and Selection: A New Perspectivecited by 28
  4. 2014A Neural Networks Committee for the Contextual Bandit Problemcited by 23
  5. 2015Random Forest for the Contextual Bandit Problem - extended versioncited by 11
  6. 2021Top-m identification for linear banditscited by 11
  7. 2017Ranking and Selection with Covariates for Personalized Decision Makingcited by 10
  8. 2017Ranking and Selection as Stochastic Controlcited by 9
  9. 2016Sensitivity to Serial Dependency of Input Processes: A Robust Approachcited by 6
  10. 2019Distributionally Robust Selection of the Bestcited by 5
  11. 2019Knowledge Gradient for Selection with Covariates: Consistency and Computationcited by 4
  12. 2020Efficient Learning for Clustering and Optimizing Context-Dependent Designscited by 4
3 more
  1. 2021Asymptotically Optimal Sampling Policy for Selecting Top-m Alternativescited by 3
  2. 2022Contextual Ranking and Selection with Gaussian Processescited by 2
  3. 2015Sequential Design for Ranking Response Surfacescited by 1

Built on by

Not cited yet.