Efficient Simulation Budget Allocation for Selecting an Optimal Subset
Chun‐Hung Chen, Donghai He, Michael C. Fu et al. · INFORMS journal on computing · 2008
We consider a class of the subset selection problem in ranking and selection. The objective is to identify the top m out of k designs based on simulated output. Traditional procedures are conservative and inefficient. Using the optimal computing budget allocation framework, we formulate the problem as that of maximizing the probability of correctly selecting all of the top-m designs subject to a constraint on the total number of samples available. For an approximation of this correct selection probability, we derive an asymptotically optimal allocation and propose an easy-to-implement heuristic sequential allocation procedure. Numerical experiments indicate that the resulting allocations are superior to other methods in the literature that we tested, and the relative efficiency increases for larger problems. In addition, preliminary numerical results indicate that the proposed new procedure has the potential to enhance computational efficiency for simulation optimization.
Cited by 236 works. doi:10.1287/ijoc.1080.0268
Authors
References
- Adaptation in Natural and Artificial Systems
- Optimal Statistical Decisions.
- Optimal Statistical Decisions
- Population-Based Incremental Learning: A Method for Integrating Genetic Search Based Function Optimization and Competitive Learning
- On Some Multiple Decision (Selection and Ranking) Rules
- Simulation modeling for analysis
- The Cross-Entropy Method: A Unified Approach to Combinatorial Optimization, Monte-Carlo Simulation and Machine Learning
- Proceedings of Winter Simulation Conference
- Simulation Budget Allocation for Further Enhancing the Efficiency of Ordinal Optimization
- Design and Analysis of Experiments for Statistical Selection, Screening and Multiple Comparisons