【Time】June 12, 2014, 15:30-16:30 

【Venue】Room N510 (Conference Room), Shunde Building 

【Title】Bayesian methods for simulation optimization 

【Speaker】Dr. Peter I. Frazier, Assistant professor, School of Operations Research and Information Engineering, Cornell University 

【Host】Dr. Lei Zhao 

【Abstract】We consider simulation optimization, in which we wish to solve an optimization problem whose objective function can only be evaluated using stochastic simulation.  When the simulator is large and time-consuming, the time to solve such problems is determined by the number of simulation replications required.  One increasingly popular approach to such problems is to place a Bayesian prior distribution on the underlying objective function, and to choose function evaluations according to the value of the information they provide.  We develop novel algorithms of this type for use in three problem settings: simulations in parallel computing environments; simulations driven by randomness with low-dimensional structure; and steady-state simulations.  We then apply these algorithms to three real-world problems: tuning algorithm parameters for the restaurant review website Yelp.com, designing cardiovascular bypass grafts, and calibrating a logistics simulator for Schneider National. 

【Bio】Peter I. Frazier is an assistant professor in the School of Operations Research and Information Engineering at Cornell University, and received a Ph.D. in Operations Research and Financial Engineering from Princeton University in 2009.  He is the recipient of an AFOSR Young Investigator Award, and an NSF CAREER Award.  He is an associate editor for Operations Research, ACM Transactions on Modeling and Computer Simulation and IIE Transactions.  His research interest is in dynamic programming and Bayesian statistics, focusing on the optimal acquisition of information and sequential design of experiments.  He works on applications in simulation, optimization, operations management, medicine, and materials science.