Professor Dirk Kroese

Professor

Mathematics
Faculty of Science
kroese@maths.uq.edu.au
+61 7 336 53287

Overview

Dirk Kroese's research interests are in: Monte Carlo methods, rare-event simulation, the cross-entropy method, applied probability, and randomised optimisation.

Dirk Kroese is a professor of Mathematics and Statistics at the School of Mathematics and Physics of the University of Queensland. He has held teaching and research positions at The University of Texas at Austin, Princeton University, the University of Twente, the University of Melbourne, and the University of Adelaide. His research interests include Monte Carlo methods, adaptive importance sampling, randomized optimization, and rare-event simulation. He has over 120 peer-reviewed publications, including six monographs:

  • Rubinstein, R.Y., Kroese, D.P. (2004). The Cross-Entropy Method: A Unified Approach to Combinatorial Optimization, Monte-Carlo Simulation, and Machine Learning, Springer, New York.
  • Rubinstein, R. Y. , Kroese, D. P. (2007). Simulation and the Monte Carlo Method, 2nd edition, John Wiley & Sons.
  • Kroese, D.P., Taimre, T., and Botev, Z.I. (2011). Handbook of Monte Carlo Methods, Wiley Series in Probability and Statistics, John Wiley & Sons, New York.
  • Kroese, D.P. and Chan, J.C.C. (2014). Statistical Modeling and Computation, Springer, New York.
  • Rubinstein, R. Y. , Kroese, D. P. (2017). Simulation and the Monte Carlo Method, 3rd edition, John Wiley & Sons.
  • Kroese, D.P, Botev, Z.I., Taimre, T and Vaisman, R. (2019) Data Science and Machine Learning: Mathematical and Statistical Methods, CRC Press.

Research Interests

  • Monte Carlo Methods
    To better understand randomness, it is useful to perform random experiments on a computer. Such "Monte Carlo simulations" are nowadays an essential ingredient in many scientific investigations. Monte Carlo can be used in several different ways: (1) to mimic a random process so as to observe its behaviour, (2) to estimate numerical quantities (e.g., multidimensional integrals) via repeated simulation, and (3) to optimise a complicated (e.g., highly multi-modal) function.
  • The Cross-Entropy Method
    The CE methods involves an iterative procedure where each iteration can be broken down into two phases: (a) generate a randon data sample (trajectories, vectors, etc.) according to a specific mechanism; (b) update the parameters of the randdom mechanism based on this data in order to produce a better sample in the next iteration. I am one of the pioneers of the CE method. The simplicity and versatility of the method is explained in my book with R.Y. Rubinstein: The Cross Entropy Method: A Unified Approach to Combinatorial Optimisation. Monte-Carlo Simulation, and Machine Learning, Springer Verlag, 2004. The CE method has been applied to problems in systems reliability, buffer allocation, telecommunication systems, neural computation, control and navigation, DNA sequence alignment, scheduling and many more.

Qualifications

  • PhD (Mathematical Sciences), Twente
  • Master of Science (Mathematical Sciences), Twente
  • Bachelor of Science (Mathematical Sciences), Twente

Publications

View all Publications

Supervision

View all Supervision

Publications

Book

Book Chapter

  • Kroese, Dirk P., Rubinstein, Reuven Y., Cohen, Izack, Porotsky, Sergey and Taimre, Thomas (2013). Cross-entropy method. Encyclopedia of operations research and management science. (pp. 326-333) edited by Saul I. Gass and Michael C. Fu. New York, United States: Springer. doi: 10.1007/978-1-4419-1153-7_131

  • Brereton, Tim J., Kroese, Dirk P. and Chan, Joshua C. (2013). Monte Carlo methods for portfolio credit risk. Credit securitisations and derivatives: challenges for the global markets. (pp. 127-152) edited by Daniel Rösch and Harald Scheule. Chicester, United Kingdom: John Wiley & Sons.

  • Kroese, Dirk P., Rubinstein, Reuven Y. and Glynn, Peter W. (2013). The cross-entropy method for estimation. Machine learning: theory and applications. (pp. 19-34) edited by Venu Govindaraju and C. R. Rao. Dordrecht, Netherlands: Elsevier. doi: 10.1016/B978-0-444-53859-8.00002-3

  • Botev, Zdravko, I., Kroese, Dirk P., Rubinstein, Reuven Y. and L'Ecuyer, Pierre (2013). The cross-entropy method for optimization. Machine learning: theory and applications. (pp. 35-59) edited by Venu Govindaraju and C. R. Rao. Dordrecht, Netherlands: Elsevier. doi: 10.1016/B978-0-444-53859-8.00003-5

  • Kroese, Dirk P. (2010). Cross-entropy method. Encyclopedia of operations research and management sciences. (pp. 1-12) New York, United States: Springer-Verlag. doi: 10.1002/9780470400531.eorms0210

  • Kroese, D. P. and Hui, Kin-Ping (2007). Applications of the cross-entropy method in reliability. Computational intelligence in reliability engineering. New metaheuristics, neural and fuzzy techniques in reliability. (pp. 37-82) edited by Gregory Levitin. Berlin, Germany: Springer-Verlag. doi: 10.1007/978-3-540-37372-8_3

Journal Article

Conference Publication

  • Botev, Zdravko, Chen, Yi-Lung, L'Ecuyer, Pierre, MacNamara, Shev and Kroese, Dirk P. (2019). Exact posterior simulation from the linear lasso regression. 2018 Winter Simulation Conference, WSC 2018, Gothenburg, Sweden, 9-12 December 2018. Piscataway, NJ, United States: Institute of Electrical and Electronics Engineers. doi: 10.1109/WSC.2018.8632237

  • Wang, Erli, Kurniawati, Hanna and Kroese, Dirk P. (2019). Inventory control with partially observable states. 23rd International Congress on Modelling and Simulation - Supporting Evidence-Based Decision Making: The Role of Modelling and Simulation, MODSIM 2019, Canberra, ACT, Australia, 1 - 6 December 2019. Modelling and Simulation Society of Australia and New Zealand Inc. (MSSANZ). doi: 10.36334/modsim.2019.B1.wang

  • Moka, Sarat Babu, Kroese, Dirk P. and Juneja, Sandeep (2019). Unbiased estimation of the reciprocal mean for non-negative random variables. 2019 Winter Simulation Conference (WSC), National Harbor, MD, United States, 8-11 December 2019. Piscataway, NJ, United States: Institute of Electrical and Electronics Engineers. doi: 10.1109/wsc40007.2019.9004815

  • Wang, Erli, Kurniawati, Hanna and Kroese, Dirk P. (2018). An on-line planner for POMDPs with large discrete action space: A quantile-based approach. 28th International Conference on Automated Planning and Scheduling ICAPS 2018, Delft, Netherlands, 24 - 29 June 2018. Menlo Park, CA United States: AAAI Press.

  • L'Ecuyer, Pierre, Botev, Zdravko I. and Kroese, Dirk P. (2018). On a generalized splitting method for sampling from a conditional distribution. 2018 Winter Simulation Conference, WSC 2018, Gothenburg, Sweden, 9-12 December 2018. Piscataway, NJ, United States: Institute of Electrical and Electronics Engineers. doi: 10.1109/WSC.2018.8632422

  • Wang, Erli, Kurniawati, Hanna and Kroese, Dirk P. (2017). CEMAB: a cross-entropy-based method for large-scale multi-armed bandits. ACALCI 2017 Australasian Conference on Artificial Life and Computational Intelligence, Geelong, VIC, Australia, 31 January – 2 February 2017. Heidelberg, Germany: Springer. doi: 10.1007/978-3-319-51691-2_30

  • Grant, Morgan R. and Kroese, Dirk P. (2017). Efficient estimation of tail probabilities of the typical distance in preferential attachment models. 2016 Winter Simulation Conference, WSC 2016, Arlington, VA, United States, 11 - 14 December 2016. Piscataway, NJ, United States: Institute of Electrical and Electronics Engineers. doi: 10.1109/WSC.2016.7822101

  • Salomone, Robert, Vaisman, Radislav and Kroese, Dirk (2016). Estimating the number of vertices in convex polytopes. 4th Annual International Conference on Operations Research and Statistics (ORS 2016), 5th Annual Conference on Computational Mathematics, Computational Geometry & Statistics (CMCGS 2016), Singapore, Singapore, 18 - 19 January 2016. Singapore, Singapore: Global Science and Technology Forum. doi: 10.5176/2251-1938_ORS16.25

  • Shah, Rohan, Hirsch, Christian, Kroese, Dirk P. and Schmidt, Volker (2015). Rare event probability estimation for connectivity of large random graphs. Winter Simulation Conference, WSC 2014, Savannah, GA, United States, 7-10 December 2014. Piscataway, NJ, United States: Institute of Electrical and Electronics Engineers. doi: 10.1109/WSC.2014.7019916

  • Brereton, Tim J., Kroese, Dirk P., Stenzel, Ole, Schmidt, Volker and Baumeier, Bjorn (2012). Efficient simulation of charge transport in deep-trap media. Winter Simulation Conference, Berlin, Germany, 9-12 December 2012. Piscataway, NJ, United States: Institute of Electrical and Electronics Engineers. doi: 10.1109/WSC.2012.6465003

  • Brereton, Tim J., Chan, Joshua C. C. and Kroese, Dirk P. (2011). Fitting mixture importance sampling distributions via improved cross-entropy. 2011 Winter Simulation Conference, Phoenix, AZ, United States, 11-14 December 2011. Piscataway, NJ, United States: IEEE. doi: 10.1109/WSC.2011.6147769

  • Stacey, Karl W. and Kroese, Dirk P. (2011). Greedy servers on a torus. 2011 Winter Simulation Conference, Phoenix, AZ, United States, 11-14 December 2011. Piscataway, NJ, United States: IEEE. doi: 10.1109/WSC.2011.6147764

  • Kothari, Rishabh P. and Kroese, Dirk P. (2009). Optimal generation expansion planning via the cross-entropy method. 2009 Winter Simulation Conference (ERA Rank B), Austin, Texas, 13-16 December 2009. United States: IEEE - Inst Electrical Electronics Engineers Inc. doi: 10.1109/WSC.2009.5429296

  • Chan, J. C. C. and Kroese, D. P. (2008). Randomized methods for solving the Winner Determination Problem in combinatorial auctions. Winter Simulation Conference 2008 (WSC 2008), Miami, United States, 7-10 December, 2008. Piscataway, NJ, U.S.A.: IEEE. doi: 10.1109/WSC.2008.4736208

  • Keith, J. M., Sofronov, G. Y. and Kroese, D. P. (2008). The Generalized Gibbs Sampler and the Neighborhood Sampler. 7th International Conference on Monte Carlo and Quasi-Monte Carlo Methods in Scientific Computing, Ulm, Germany, 14-18 August, 2006. Berlin: Springer-Verlag. doi: 10.1007/978-3-540-74496-2_31

  • Sofronov, G. Y., Evans, G. E., Keith, J. M. and Kroese, D. P. (2007). Identifying change-points in biological sequences via sequential importance sampling. 17th Biennial Congress on Modelling and Simulation (MODSIM07), Christchurch, New Zealand, 10-13 December, 2007. Christchurch, New Zealand: Modelling and Simulation Society of Australia and New Zealand.

  • Sani, A. and Kroese, D. P. (2007). Optimal epidemic intervention of HIV spread using the cross-entropy method. 17th Biennial Congress on Modelling and Simulation (MODSIM07), Christchurch, New Zealand, 10-13 December, 2007. Christchurch, New Zealand: Modelling and Simulation Society of Australia and New Zealand.

  • Evans, G. E., Keith, J. M. and Kroese, D. P. (2007). Parallel cross-entropy optimization. 2007 Winter Simulation Conference, Washington, 9-12 December, 2007. Washington: IEEE. doi: 10.1145/1360000/1351930/p2196-evans.pdf?key1=1351930

  • Botev, Z. I., Kroese, D. P. and Taimre, T. (2006). Generalized cross-entropy methods for rare events and optimization. 6th International Workshop on Rare Event Simulation (RESIM 2006), Bamberg, Germany, 8-10 October, 2006.

  • Nariai, Sho, Hui, Kin-Ping and Kroese, Dirk P. (2005). Designing an optimal network using the cross-entropy method. Sixth International Conference on Intelligent Data Engineering and Automated Learning (IDEAL 2005), Brisbane, Australia, 6-8 July 2005. Heidelberg, Germany: Springer. doi: 10.1007/11508069_30

  • Nariai, S. and Kroese, D. P. (2005). On the Design of Multi-type Networks via the Cross-Entropy Method. DRCN 2005, Naples, Italy, 16-19 October 2005. Italy: IEEE. doi: 10.1109/DRCN.2005.1563852

  • Botev, Zdravko and Kroese, Dirk P. (2004). Global likelihood optimization via the cross-entropy method with an application to mixture models.

  • Botev, Z. I. and Kroese, D. P. (2004). Global Likelihood Optimization Via The Cross-Entropy Method With An Application To Mixture Models. 2004 Winter Simulation Conference, Washington, USA, 5-8 December, 2004. Washington: Board of Winter Simulation Conference.

  • Kroese, D. P. and Rubinstein, R. Y. (2004). The transform likelihood ratio method for rare event simulation with heavy tails. United States: Springer New York LLC. doi: 10.1023/B:QUES.0000027989.97672.be

  • Hui, K.-P., Bean, N.G., Kraetzl, M. and Kroese, D. P. (2003). Network reliability estimation using the tree cut and merge algorithm with importance sampling. DRCN2003, Banff, Canada, 19-22 October 2003. Canada: The Institute of Electrical & Electronics Engineers, Inc. doi: 10.1109/DRCN.2003.1275364

  • de Boer, P.T., Kroese, D. P. and Rubinstein, R.Y. (2002). Estimating buffer overflows in three stages using cross-entropy. 35th Winter Simulation Conference (ERA Rank B), San Diego, USA, 3-11 December 2002. United States: IEEE - Computer Society. doi: 10.1109/WSC.2002.1172899

  • Keith, Jonathan and Kroese, Dirk P. (2002). Sequence alignment by rare event simulation. 35th 2002 Winter Simulation Conference (ERA Rank B), San Diego, CA, U.S.A., 8-11 December 2002. United States: IEEE - Computer Society. doi: 10.1109/WSC.2002.1172901

  • Kroese, Dirk P. and Nicola, Victor F. (1999). Efficient simulation of a tandem Jackson network. 1999 Winter Simulation Conference Proceedings (WSC), , , December 5, 1999-December 8, 1999.

  • Garvels, Marnix J J and Kroese, Dirk P. (1998). Comparison of RESTART implementations. Proceedings of the 1998 Winter Simulation Conference, WSC. Part 1 (of 2), , , December 13, 1998-December 16, 1998. IEEE.

  • Garvels, M. J. J . and Kroese, D. P. (1998). A comparison of RESTART implementations. Winter Simulation Conference, Washington, DC, United States, 13-16 Dec 1998.

  • Kroese, DP and Nicola, VF (1998). Efficient simulation of backlogs in fluid flow lines. Workshop on Rare Event Simulation, Aachen Germany, Aug 28-29, 1997. JENA: GUSTAV FISCHER VERLAG.

Edited Outputs

Other Outputs

Grants (Administered at UQ)

PhD and MPhil Supervision

Current Supervision

  • Doctor Philosophy — Associate Advisor

    Other advisors:

  • Doctor Philosophy — Associate Advisor

  • Doctor Philosophy — Associate Advisor

    Other advisors:

  • Doctor Philosophy — Associate Advisor

Completed Supervision