• Corpus ID: 218869891

Reactive Sample Size for Heuristic Search in Simulation-based Optimization

  title={Reactive Sample Size for Heuristic Search in Simulation-based Optimization},
  author={Manuel Dalcastagn'e and Andrea Mariello and Roberto Battiti},
In simulation-based optimization, the optimal setting of the input parameters of the objective function can be determined by heuristic optimization techniques. However, when simulators model the stochasticity of real-world problems, their output is a random variable and multiple evaluations of the objective function are necessary to properly compare the expected performance of different parameter settings. This paper presents a novel reactive sample size algorithm based on parametric tests and… 
1 Citations

Heuristic Search Strategies for Noisy Optimization

Results show that this extension of randomized heuristic search strategies non based on populations with a statistical analysis technique can outperform population-based algorithms, especially with higher levels of noise.



Chapter 20 An Overview of Simulation Optimization via Random Search

Simulation-Based Optimization: Parametric Optimization Techniques and Reinforcement Learning

This book examines the mathematical governing principles of simulation-based optimization, thereby providing the reader with the ability to model relevant real-life problems using these techniques, and outlines the computational technology underlying these methods.

Variable-sample methods for stochastic optimization

This article discusses the application of a certain class of Monte Carlo methods to stochastic optimization problems by studying a modification of the well-known pure random search method, adapting it to the variable-sample scheme, and showing conditions for convergence of the algorithm.

Adaptive random search for continuous simulation optimization

The adaptive search with resampling (ASR) approach is a framework for designing provably convergent algorithms that are adaptive and may consequently involve local search, and conditions under which the three methods are convergent are presented.

Simulation optimization: a review of algorithms and applications

The difficulties in SO as compared to algebraic model-based mathematical programming are emphasized, the different approaches used are examined, some of the diverse applications that have been tackled by these methods are reviewed, and future directions in the field are speculates.

Improving Hit-and-Run with single observations for continuous simulation optimization

Instead of averaging replications of the objective function at a specific point (e.g., sample average), this paper average observed function evaluations from neighboring points to suggest an efficiency with single observations per sample point that simultaneously improves the estimation of the function value and samples closer to the optimum as the algorithm progresses.

Using Ranking and Selection to "Clean Up" after Simulation Optimization

This paper develops statistical procedures that return the best system encountered by the search (or one near the best) with a prespecified probability, using combinations of statistical subset selection and indifference-zone ranking procedures.

A sequential procedure for neighborhood selection-of-the-best in optimization via simulation

On Choosing Parameters in Retrospective-Approximation Algorithms for Stochastic Root Finding and Simulation Optimization

This paper presents an overview of the conditions that guarantee the correct convergence of RA's iterates, and characterize a class of error-tolerance and sample-size sequences that are superior to others in a certain precisely defined sense.

A fully sequential procedure for indifference-zone selection in simulation

The procedures presented are appropriate when it is possible to repeatedly obtain small, incremental samples from each simulated system and are based on the assumption of normally distributed data, so the impact of batching is analyzed.