Optimal sampling laws for bi-objective simulation optimization on finite sets. Hunter, S. R. & Feldman, G. In Yilmaz, L., Chan, W. K. V., Moon, I., Roeder, T. M. K., Macal, C., & Rossetti, M. D., editors, Proceedings of the 2015 Winter Simulation Conference, pages 3749–3757, Piscataway, NJ, 2015. Institute of Electrical and Electronics Engineers, Inc.. Paper doi abstract bibtex We consider the bi-objective simulation optimization (SO) problem on finite sets, that is, an optimization problem where for each ``system'' the two objective functions are estimated as output from a Monte Carlo simulation. The solution to this bi-objective SO problem is a set of non-dominated systems, also called the Pareto set. In this context, we derive the large deviations rate function for the rate of decay of the probability of a misclassification event as a function of the proportion of sample allocated to each competing system. Notably, we account for the presence of dependence between the estimates of each system's performance on the two objectives. The asymptotically optimal allocation maximizes the rate of decay of the probability of misclassification and is the solution to a concave maximization problem.
@inproceedings{2015hunfelWSC,
Year = {2015},
Author = {S. R. Hunter and G. Feldman},
Title = {Optimal sampling laws for bi-objective simulation optimization on finite sets},
Booktitle = {Proceedings of the 2015 Winter Simulation Conference},
Editor = {L. Yilmaz and W. K. V. Chan and I. Moon and T. M. K. Roeder and C. Macal and M. D. Rossetti},
Publisher = {Institute of Electrical and Electronics Engineers, Inc.},
Address = {Piscataway, NJ},
Pages = {3749--3757},
doi = {10.1109/WSC.2015.7408532},
url_Paper = {http://www.informs-sim.org/wsc15papers/424.pdf},
abstract = {We consider the bi-objective simulation optimization (SO) problem on finite sets, that is, an optimization problem where for each ``system'' the two objective functions are estimated as output from a Monte Carlo simulation. The solution to this bi-objective SO problem is a set of non-dominated systems, also called the Pareto set. In this context, we derive the large deviations rate function for the rate of decay of the probability of a misclassification event as a function of the proportion of sample allocated to each competing system. Notably, we account for the presence of dependence between the estimates of each system's performance on the two objectives. The asymptotically optimal allocation maximizes the rate of decay of the probability of misclassification and is the solution to a concave maximization problem.},
keywords = {simulation optimization > multi-objective > ranking and selection}}
Downloads: 0
{"_id":"tkbaxvTWfpzyziodx","bibbaseid":"hunter-feldman-optimalsamplinglawsforbiobjectivesimulationoptimizationonfinitesets-2015","author_short":["Hunter, S. R.","Feldman, G."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","year":"2015","author":[{"firstnames":["S.","R."],"propositions":[],"lastnames":["Hunter"],"suffixes":[]},{"firstnames":["G."],"propositions":[],"lastnames":["Feldman"],"suffixes":[]}],"title":"Optimal sampling laws for bi-objective simulation optimization on finite sets","booktitle":"Proceedings of the 2015 Winter Simulation Conference","editor":[{"firstnames":["L."],"propositions":[],"lastnames":["Yilmaz"],"suffixes":[]},{"firstnames":["W.","K.","V."],"propositions":[],"lastnames":["Chan"],"suffixes":[]},{"firstnames":["I."],"propositions":[],"lastnames":["Moon"],"suffixes":[]},{"firstnames":["T.","M.","K."],"propositions":[],"lastnames":["Roeder"],"suffixes":[]},{"firstnames":["C."],"propositions":[],"lastnames":["Macal"],"suffixes":[]},{"firstnames":["M.","D."],"propositions":[],"lastnames":["Rossetti"],"suffixes":[]}],"publisher":"Institute of Electrical and Electronics Engineers, Inc.","address":"Piscataway, NJ","pages":"3749–3757","doi":"10.1109/WSC.2015.7408532","url_paper":"http://www.informs-sim.org/wsc15papers/424.pdf","abstract":"We consider the bi-objective simulation optimization (SO) problem on finite sets, that is, an optimization problem where for each ``system'' the two objective functions are estimated as output from a Monte Carlo simulation. The solution to this bi-objective SO problem is a set of non-dominated systems, also called the Pareto set. In this context, we derive the large deviations rate function for the rate of decay of the probability of a misclassification event as a function of the proportion of sample allocated to each competing system. Notably, we account for the presence of dependence between the estimates of each system's performance on the two objectives. The asymptotically optimal allocation maximizes the rate of decay of the probability of misclassification and is the solution to a concave maximization problem.","keywords":"simulation optimization > multi-objective > ranking and selection","bibtex":"@inproceedings{2015hunfelWSC,\n\tYear = {2015},\n\tAuthor = {S. R. Hunter and G. Feldman},\n\tTitle = {Optimal sampling laws for bi-objective simulation optimization on finite sets},\n\tBooktitle = {Proceedings of the 2015 Winter Simulation Conference},\n\tEditor = {L. Yilmaz and W. K. V. Chan and I. Moon and T. M. K. Roeder and C. Macal and M. D. Rossetti},\n\tPublisher = {Institute of Electrical and Electronics Engineers, Inc.},\n Address = {Piscataway, NJ},\n Pages = {3749--3757},\n doi = {10.1109/WSC.2015.7408532},\n url_Paper = {http://www.informs-sim.org/wsc15papers/424.pdf},\n abstract = {We consider the bi-objective simulation optimization (SO) problem on finite sets, that is, an optimization problem where for each ``system'' the two objective functions are estimated as output from a Monte Carlo simulation. The solution to this bi-objective SO problem is a set of non-dominated systems, also called the Pareto set. In this context, we derive the large deviations rate function for the rate of decay of the probability of a misclassification event as a function of the proportion of sample allocated to each competing system. Notably, we account for the presence of dependence between the estimates of each system's performance on the two objectives. The asymptotically optimal allocation maximizes the rate of decay of the probability of misclassification and is the solution to a concave maximization problem.},\n\tkeywords = {simulation optimization > multi-objective > ranking and selection}}\n\n","author_short":["Hunter, S. R.","Feldman, G."],"editor_short":["Yilmaz, L.","Chan, W. K. V.","Moon, I.","Roeder, T. M. K.","Macal, C.","Rossetti, M. D."],"key":"2015hunfelWSC","id":"2015hunfelWSC","bibbaseid":"hunter-feldman-optimalsamplinglawsforbiobjectivesimulationoptimizationonfinitesets-2015","role":"author","urls":{" paper":"http://www.informs-sim.org/wsc15papers/424.pdf"},"keyword":["simulation optimization > multi-objective > ranking and selection"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"inproceedings","biburl":"https://web.ics.purdue.edu/~hunter63/PAPERS/srhunterweb.bib","dataSources":["ZEwmdExPMCtzAbo22","PkcXzWbdqPvM6bmCx"],"keywords":["simulation optimization > multi-objective > ranking and selection"],"search_terms":["optimal","sampling","laws","objective","simulation","optimization","finite","sets","hunter","feldman"],"title":"Optimal sampling laws for bi-objective simulation optimization on finite sets","year":2015}