Convergence rate analysis for optimal computing budget allocation algorithms

DOI10.1016/j.automatica.2023.111042zbMath1520.93316arXiv2211.14722OpenAlexW4365520216MaRDI QIDQ6110297

Siyang Gao, YanWen Li

Publication date: 5 July 2023

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2211.14722

zbMATH Keywords

ordinal optimizationoptimal convergence rateranking and selectionoptimal computing budget allocationdiscrete-event dynamic system

Mathematics Subject Classification ID

Nonconvex programming, global optimization (90C26) Discrete event control/observation systems (93C65)

Cites Work

• Unnamed Item
• Efficient subset selection for the expected opportunity cost
• Asymptotically efficient adaptive allocation rules
• Ordinal optimization of DEDS
• Bonferroni inequalities
• Efficient global optimization of expensive black-box functions
• Convergence properties of ordinal comparison in the simulation of discrete event dynamic systems
• Simulation budget allocation for further enhancing the efficiency of ordinal optimization
• Simulation budget allocation for simultaneously selecting the best and worst subsets
• An efficient simulation procedure for ranking the top simulated designs in the presence of stochastic constraints
• Bayesian look ahead one-stage sampling allocations for selection of the best population
• Robust ranking and selection with optimal computing budget allocation
• Optimal computing budget allocation for the vector evaluated genetic algorithm in multi-objective simulation optimization
• Optimal computing budget allocation for regression with gradient information
• The Knowledge Gradient Algorithm for a General Class of Online Learning Problems
• Sequential Sampling to Myopically Maximize the Expected Value of Information
• On the Convergence Rates of Expected Improvement Methods
• Selecting a Selection Procedure
• Ordinal optimisation and simulation
• Application of discrete-event simulation in health care clinics: A survey
• A Knowledge-Gradient Policy for Sequential Information Collection
• Improved Risk Tail Bounds for On-Line Algorithms
• Pure Exploration in Multi-armed Bandits Problems
• Optimal Adaptive Policies for Markov Decision Processes
• A fully sequential procedure for indifference-zone selection in simulation
• A New Budget Allocation Framework for the Expected Opportunity Cost
• Sample mean based index policies by O(log n) regret for the multi-armed bandit problem
• An Optimal Computing Budget Allocation Tree Policy for Monte Carlo Tree Search
• Introduction to Multi-Armed Bandits
• Stochastically Constrained Ranking and Selection via SCORE
• Myopic Allocation Policy With Asymptotically Optimal Sampling Rate
• Approximate Simulation Budget Allocation for Selecting the Best Design in the Presence of Stochastic Constraints
• Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems
• Finite-time analysis of the multiarmed bandit problem