Heavy tails, importance sampling and cross-entropy

Stochastic Models

Volumn 21, Issue 1, 2005, Pages 57-76

  Asmussen, Søren ^a   Kroese, Dirk P ^b   Rubinstein, Reuven Y ^c  

^a AARHUS UNIVERSITY   (Denmark)

^b UNIVERSITY OF QUEENSLAND   (Australia)

^c TECHNION ISRAEL INSTITUTE OF TECHNOLOGY   (Israel)

Author keywords

Algorithmic complexity; Cross entropy; GI G 1 queue; Importance sampling; M G 1 queue; Maximum likelihood; Pareto distribution; Pollaczek Khintchine formula; Random walk; Rare event; Subexponential distribution; Weibull distribution

Indexed keywords

ALGORITHMS; COMPUTATIONAL COMPLEXITY; ENTROPY; MAXIMUM LIKELIHOOD ESTIMATION; PARAMETER ESTIMATION; PARETO PRINCIPLE; PROBLEM SOLVING; RANDOM PROCESSES; WEIBULL DISTRIBUTION;

ALGORITHMIC COMPLEXITY; CROSS-ENTROPY; GI/G/1 QUEUE; POLLACZEK-KHINTCHINE FORMULA; RANDOM WALK; RARE EVENT; SUBEXPONENTIAL DISTRIBUTION;

SAMPLING;

EID: 17444380191     PISSN: 15326349     EISSN: 15324214     Source Type: Journal    
DOI: 10.1081/STM-200046472     Document Type: Article

References (19)

1. Adler, R. J.; Feldman, R.; Taqqu, M. S. A User's Guide to Heavy Tails; Birkhäuser, Germany, 1998.
2. Asmussen, S. Ruin Probabilities; World Scientific: Singapore, 2000.
3. Asmussen, S. Applied Probability and Queues; Springer-Verlag: New York, 2003.
4. Asmussen, S.; Binswanger, K. Simulation of ruin probabilities for subexponential claims. ASTIN Bulletin. 1997, 27, 297-318.
5. Asmussen, S.; Binswanger, K.; Højgaard, B. Rare events simulation for heavy-tailed distributions. Bernoulli. 2000, 6, 303-322.
6. Asmussen, S.; Rubinstein, R. Y. Steady-state rare events simulation in queueing models and its complexity properties. In Advances in Queueing: Models, Methods and Problems; (Dshalalow, J. ed.); CRC Press: Boca Raton, FL, 1995; 429-466.
7. de Boer, P. T.; Kroese, D. P.; Rubinstein, R. Y. Estimating buffer overflows in three stages using cross-entropy. In Proceedings of the 2002 Winter Simulation Conference; San Diego, 2003, 301-309.
8. de Boer, P. T.; Kroese, D. P.; Mannor, S.; Rubinstein, R. Y. A tutorial on the cross-entropy method. Ann. Op. Res. 2004, 134, 19-67.
9. Boots, N. K.; Shahabuddin, P. Simulating tail probabilities in GI/G/1 queues and insurance risk processes with subexponential distributions. Proceedings of the 2001 Winter Simulation Conference; San Diego, 2002, 468-476.
10. Embrechts, P.; Klüppelberg, C.; Mikosch, T. Modeling Extremal Events for Finance and Insurance; Springer-Verlag: Dodrecht, The Netherlands, 1997.
11. Heidelberger, P. Fast simulation of rare events in queueing and reliability models. ACM TOMACS. 1995, 6, 43-85.
12. Homem de Mello, T.; Rubinstein, R. Y. Rare event probability estimation for static models via cross-entropy and importance sampling. Submitted.
13. Juneja, S.; Shahabuddin, P. Simulating heavy tailed processes using delayed hazard rate twisting. ACM TOMACS. 2002, 12, 94-118.
14. Kroese, D. P.; Rubinstein, R. Y. The transform likelihood ratio method for rare event simulation with heavy tails. Queueing Systems. 2004, 46, 317-351.
15. Rubinstein, R. Y. Optimization of computer simulation models with rare events. Eur. J. Oper. Res. 1997, 99, 89-112.
16. Rubinstein, R. Y. The cross-entropy method for combinatorial and continuous optimization. Method. Comput. Appl. Probab. 1999, 2, 127-190.
17. Rubinstein, R. Y.; Kroese, D. P. The Cross-Entropy Method. A Unified Approach to Combinatorial Optimization, Monte-Carlo Simulation and Machine Learning; Springer-Verlag, New York, USA, 2004.
18. Rubinstein, R. Y.; Melamed, B. Modern Simulation and Modeling; Wiley: London, UK, 1998.
19. Sigman, K. A primer on heavy-tailed distributions. Queueing Systems. 1999, 33, 261-275.