An improved simulation budget allocation procedure to efficiently select the optimal subset of many alternatives

How to maximize the probability of correctly selecting the top-m designs out of k designs under a computing budget constraint is crucial in simulation optimization. We develop a new procedure to be more efficient and robust than existing ones. The asymptotic convergence rate of this new procedure achieves higher convergence rate than others in correct selection probability for subset selection problems. Numerical experiments show that the new procedure obtains a higher probability of correctly selecting the optimal subset under the same computing budget.