On the Convergence Rates of Expected Improvement Methods
From MaRDI portal
Publication:2957473
DOI10.1287/opre.2016.1494zbMath1359.62519OpenAlexW2401855953MaRDI QIDQ2957473
Publication date: 26 January 2017
Published in: Operations Research (Search for Journal in Brave)
Full work available at URL: https://semanticscholar.org/paper/576c3122675cb0e123c5288a3142d30d58527d8c
Applications of statistics to economics (62P20) Bayesian problems; characterization of Bayes procedures (62C10) Decision theory (91B06) Sequential statistical design (62L05)
Related Items (18)
Solving Large-Scale Fixed-Budget Ranking and Selection Problems ⋮ Dynamic Sampling Allocation Under Finite Simulation Budget for Feasibility Determination ⋮ Optimal computing budget allocation for regression with gradient information ⋮ Technical note—Knowledge gradient for selection with covariates: Consistency and computation ⋮ Ranking and selection for pairwise comparison ⋮ Sequential selection for accelerated life testing via approximate Bayesian inference ⋮ Asymptotic optimality of myopic ranking and selection procedures ⋮ Convergence rate analysis for optimal computing budget allocation algorithms ⋮ Technical Note—Consistency Analysis of Sequential Learning Under Approximate Bayesian Inference ⋮ A unified framework for stochastic optimization ⋮ Simple Bayesian Algorithms for Best-Arm Identification ⋮ Bayesian sequential data collection for stochastic simulation calibration ⋮ Expected improvement for expensive optimization: a review ⋮ Complete expected improvement converges to an optimal budget allocation ⋮ The Local Time Method for Targeting and Selection ⋮ Efficient Sampling Allocation Procedures for Optimal Quantile Selection ⋮ Cross-Validation--based Adaptive Sampling for Gaussian Process Models ⋮ Optimal budget allocation policy for tabu search in stochastic simulation optimization
Uses Software
Cites Work
- Asymptotically efficient adaptive allocation rules
- Efficient global optimization of expensive black-box functions
- Simulation budget allocation for further enhancing the efficiency of ordinal optimization
- Bayesian look ahead one-stage sampling allocations for selection of the best population
- The Knowledge Gradient Algorithm for a General Class of Online Learning Problems
- Simulation Allocation for Determining the Best Design in the Presence of Correlated Sampling
- Sequential Sampling to Myopically Maximize the Expected Value of Information
- Information Collection on a Graph
- Selecting a Selection Procedure
- A Knowledge-Gradient Policy for Sequential Information Collection
- Sequential Selection with Unknown Correlation Structures
- Rational Bounds for the t-Tail Area
- An Asymptotic Expansion for the Tail Area of the t-Distribution
- Learning to Optimize via Posterior Sampling
- Convergence rates of efficient global optimization algorithms
- Asymptotic Tail Properties of Student'st-Distribution
This page was built for publication: On the Convergence Rates of Expected Improvement Methods