Bayesian sequential data collection for stochastic simulation calibration. (English) Zbl 1430.62062
Summary: Simulation is often used to guide the decision making for real complex stochastic systems. To faithfully assess the mean performance of the real system, it is necessary to efficiently calibrate the simulation model. Existing calibration approaches are typically built on the summary statistics of simulation outputs and ignore the serial dependence of detailed output sample paths. Given a tight simulation budget, we develop a Bayesian sequential data collection approach for simulation calibration via exploring the detailed simulation outputs. Then, the calibrated simulation model can be used to guide decision making. Both theoretical and empirical studies demonstrate that we can efficiently use the simulation resources and achieve better calibration accuracy by exploring the first two moment dynamic information of simulation output sample paths.
Keywords:
simulation; calibration; sequential experiment design; detailed sample paths; Bayesian methodReferences:
| [1] | Carnell, R. (2016). lhs: Latin hypercube samples. R package version 0.14.; Carnell, R. (2016). lhs: Latin hypercube samples. R package version 0.14. |
| [2] | Cressie, N.; Johannesson, G., Fixed rank Kriging for very large spatial data sets, Journal of the Royal Statistical Society: Series B (Statistical Methodology), 70, 1, 209-226 (2008) · Zbl 05563351 |
| [3] | Frazier, P.; Powell, W. B.; Simaão, H. P., Simulation model calibration with correlated knowledge-gradients, (Rossetti, M. D.; Hill, R. R.; Johansson, B.; Dunkin, A.; Ingalls, R. G., Proceedings of the 2009 winter simulation conference (2009), Institute of Electrical and Electronics Engineers, Inc: Institute of Electrical and Electronics Engineers, Inc Piscataway, New Jersey), 339-351 |
| [4] | Frazier, P. I.; Powell, W. B.; Dayanik, S., A knowledge-gradient policy for sequential information collection, SIAM Journal on Control and Optimization, 47, 5, 2410-2439 (2008) · Zbl 1274.62155 |
| [5] | Goeva, A.; Lam, H.; Zhang, B., Reconstructing input models via simulation optimization, (Tolk, A.; Diallo, S. Y.; Ryzhov, I. O.; Yilmaz, L.; Buckley, S.; Miller, J. A., Proceedings of the 2014 winter simulation conference (2014), Institute of Electrical and Electronics Engineers, Inc: Institute of Electrical and Electronics Engineers, Inc Piscataway, New Jersey), 698-709 |
| [6] | Gramacy, R. B.; Bingham, D.; Holloway, J. P.; Grosskopf, M. J.; Kuranz, C. C.; Rutter, E., Calibrating a large computer experiment simulating radiative shock hydrodynamics, The Annals of Applied Statistics, 9, 3, 1141-1168 (2015) · Zbl 1454.62530 |
| [7] | Horiguchi, K.; Raghavan, N.; Uzsoy, R.; Venkateswaran, S., Finite-capacity production planning algorithms for a semiconductor wafer fabrication facility, International Journal of Production Research, 39, 5, 825-842 (2001) · Zbl 1060.90563 |
| [8] | Kennedy, M. C.; O’Hagan, A., Bayesian calibration of computer models, Journal of the Royal Statistical Society: Series B (Statistical Methodology), 63, 3, 425-464 (2001) · Zbl 1007.62021 |
| [9] | Lin, Y.; Nelson, B. L., Simulation analytics for virtual statistics via k nearest neighbors, (Roeder, T. M.K.; Frazier, P. I.; Szechtman, R.; Zhou, E.; Huschka, T.; Chick, S. E., Proceedings of the 2016 winter simulation conference (2016), Institute of Electrical and Electronics Engineers, Inc: Institute of Electrical and Electronics Engineers, Inc Piscataway, New Jersey), 448-459 |
| [10] | Luo, J.; Hong, L. J.; Nelson, B. L.; Wu, Y., Fully sequential procedures for large-scale ranking-and-selection problems in parallel computing environments, Operations Research, 63, 5, 1177-1194 (2015) · Zbl 1347.68151 |
| [11] | Nelson, B. L., ‘some tactical problems in digital simulation’ for the next 10 years, Journal of Simulation, 10 (2016) |
| [12] | Plumlee, M., Bayesian calibration of inexact computer models, Journal of the American Statistical Association, 112, 519, 1274-1285 (2017) |
| [13] | Plumlee, M.; Lam, H., Fourier trajectory analysis for identifying system congestion, (Roeder, T. M.K.; Frazier, P. I.; Szechtman, R.; Zhou, E.; Huschka, T.; Chick, S. E., Proceedings of the 2016 winter simulation conference (2016), Institute of Electrical and Electronics Engineers, Inc: Institute of Electrical and Electronics Engineers, Inc Piscataway, New Jersey), 401-412 |
| [14] | Plumlee, M.; Lam, H., Learning stochastic model discrepancy, (Roeder, T. M.K.; Frazier, P. I.; Szechtman, R.; Zhou, E.; Huschka, T.; Chick, S. E., Proceedings of the 2016 winter simulation conference (2016), Institute of Electrical and Electronics Engineers, Inc: Institute of Electrical and Electronics Engineers, Inc Piscataway, New Jersey), 413-424 |
| [15] | Powell, W. B.; Ryzhov, I. O., Optimal Learning (2012), John Wiley and Sons |
| [16] | Qu, H.; Ryzhov, I. O.; Fu, M. C.; Ding, Z., Sequential selection with unknown correlation structures, Operations Research, 63, 4, 931-948 (2015) · Zbl 1329.62474 |
| [17] | Ryzhov, I. O., On the convergence rates of expected improvement methods, Operations Research, 64, 6, 1515-1528 (2016) · Zbl 1359.62519 |
| [18] | Ryzhov, I. O., The local time method for targeting and selection, Operations Research (2018) · Zbl 1456.62031 |
| [19] | Scott, W.; Frazier, P.; Powell, W., The correlated knowledge gradient for simulation optimization of continuous parameters using gaussian process regression, SIAM Journal on Optimization, 21, 3, 996-1026 (2011) · Zbl 1229.62018 |
| [20] | Tuo, R.; Wu, C. F.J., A theoretical framework for calibration in computer models: parametrization, estimation and convergence properties, SIAM/ASA Journal on Uncertainty Quantification, 4, 1, 767-795 (2016) · Zbl 1383.62354 |
| [21] | Tuo, R.; Wu, C. J., Efficient calibration for imperfect computer models, The Annals of Statistics, 43, 6, 2331-2352 (2015) · Zbl 1326.62228 |
| [22] | Wang, B.; Zhang, Q.; Xie, W., Bayesian sequential calibration using detailed sample paths, Proceedings of the 2017 winter simulation conference (wsc), 1962-1973 (2017) |
| [23] | Whittle, P., On stationary processes in the plane, Biometrika, 434-449 (1954) · Zbl 0058.35601 |
| [24] | Wong, R. K.W.; Storlie, C. B.; Lee, T. C.M., A frequentist approach to computer model calibration, Journal of the Royal Statistical Society: Series B (Statistical Methodology), 79, 2, 635-648 (2017) · Zbl 1414.62079 |
| [25] | Yuan, J.; Ng, S. H., An entropy based sequential calibration approach for stochastic computer models, (Pasupathy, R.; Kim, S.-H.; Tolk, A.; Hill, R.; Kuhl, M. E., Proceedings of the 2013 winter simulation conference (2013), Institute of Electrical and Electronics Engineers, Inc: Institute of Electrical and Electronics Engineers, Inc Piscataway, New Jersey), 589-600 |
| [26] | Yuan, J.; Ng, S. H.; Tsui, K. L., Calibration of stochastic computer models using stochastic approximation methods, IEEE Transactions on Automation Science and Engineering, 10, 1, 171-186 (2013) |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
