Complete expected improvement converges to an optimal budget allocation

DOI10.1017/APR.2019.9zbMATH Open1428.62038OpenAlexW2964059559MaRDI QIDQ5203897FDOQ5203897

Authors: Ye Chen, Ilya O. Ryzhov 

Publication date: 9 December 2019

Published in: Advances in Applied Probability (Search for Journal in Brave)

Full work available at URL: https://www.cambridge.org/core/services/aop-cambridge-core/content/view/5F61B13648DDAED930B5AB0889B5D134/S0001867819000090a.pdf/complete_expected_improvement_converges_to_an_optimal_budget_allocation.pdf

Recommendations

• On the convergence rates of expected improvement methods
• Dynamic sampling allocation and design selection
• Sequential sampling to myopically maximize the expected value of information
• Consistency of sequential Bayesian sampling policies
• Convergence rates of efficient global optimization algorithms

zbMATH Keywords

ranking and selectionexpected improvementoptimal learninglarge deviations rate

Mathematics Subject Classification ID

Applications of statistics to economics (62P20) Statistical ranking and selection procedures (62F07) Bayesian problems; characterization of Bayes procedures (62C10)

Cites Work

• Efficient global optimization of expensive black-box functions
• Title not available (Why is that?)
• Multi-armed bandit allocation indices. With a foreword by Peter Whittle.
• A Single-Sample Multiple Decision Procedure for Ranking Means of Normal Populations with known Variances
• Selecting a selection procedure
• Simulation budget allocation for further enhancing the efficiency of ordinal optimization
• A fully sequential procedure for indifference-zone selection in simulation
• Stochastically Constrained Ranking and Selection via SCORE
• Learning to Optimize via Posterior Sampling
• Title not available (Why is that?)
• Sequential sampling to myopically maximize the expected value of information
• On the Convergence Rates of Expected Improvement Methods
• Simple Bayesian Algorithms for Best-Arm Identification
• Optimal Learning in Linear Regression with Combinatorial Feature Selection
• Myopic Allocation Policy With Asymptotically Optimal Sampling Rate

Cited In (7)

• Optimal budget allocation policy for tabu search in stochastic simulation optimization
• Using cache or credit for parallel ranking and selection
• Sequential selection for accelerated life testing via approximate Bayesian inference
• Optimal computing budget allocation for regression with gradient information
• Contextual ranking and selection with Gaussian processes and optimal computing budget allocation
• On the finite-sample statistical validity of adaptive fully sequential procedures
• Rapid Discrete Optimization via Simulation with Gaussian Markov Random Fields

Uses Software

• EGO

This page was built for publication: Complete expected improvement converges to an optimal budget allocation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5203897)