- Assistant Professor, Systems and Industrial Engineering
- Assistant Professor, Applied Mathematics - GIDP
Matthias Poloczek is an assistant professor in the Department of Systems and Industrial Engineering at the University of Arizona. He is also affiliated with the Applied Math Graduate Interdisciplinary Program.
Before joining UA, he worked as postdoctoral researcher with David P. Williamson and Peter I. Frazier at Cornell University, Ithaca NY. His research was partially supported by a Feodor Lynen Research Fellowship of the Alexander von Humboldt Foundation. Dr. Poloczek obtained his PhD from the Goethe-University Frankfurt in 2013, advised by Georg Schnitger.
- Oral presentation at NIPS 2017
- NIPS, Fall 2017
- Spotlight presentation NIPS 2017
- NIPS, Fall 2017
- Award for outstanding academic performance and for the best Ph.D. in computer science
- Goethe University Frankfurt am Main, Spring 2013
- Award for outstanding academic performance and the best diploma in computer science
- Goethe University Frankfurt am Main, Spring 2008
SIE 575 Bayesian Machine Learning(see https://sie.engineering.arizona.edu/sites/sie.engineering.arizona.edu/files/syllabus/SIE-575_Syllabus-Spring_2018.pdf )SIE 474/574 Information Analytics and Decision-Making in Engineering(see https://sie.engineering.arizona.edu/sites/sie.engineering.arizona.edu/files/syllabus/SIE-474-574_Syllabus-Spring_2018_0.pdf )
I design and analyze algorithms at the intersection of machine learning and optimization. Specifically, I develop algorithms that are fast in practice and provide provable performance guarantees.Research topics:- Bayesian optimization, in particular for design of experiments, hyperparameter tuning- Approximation algorithms for combinatorial optimization- Applications in aerospace engineering, energy, and materials discovery
Independent StudySIE 599 (Spring 2018)
Special Topics in SIESIE 496 (Spring 2018)
Special Topics in SIESIE 596 (Spring 2018)
Topics Of OptimizationSIE 649 (Fall 2017)
- Baptista, R., & Poloczek, M. (2018). Bayesian Optimization of Combinatorial Structures. Proc. of Thirty-fifth International Conference on Machine Learning (ICML).More infoThe code is available at https://github.com/baptistar/BOCS
- Poloczek, M., & Williamson, D. P. (2017). An Experimental Evaluation of Fast Approximation Algorithms for the Maximum Satisfiability Problem. J. Exp. Algorithmics, 22, 1.6:1--1.6:18.
- Poloczek, M., Schnitger, G., Williamson, D. P., & Van, Z. A. (2017). Greedy algorithms for the maximum satisfiability problem: Simple algorithms and inapproximability bounds. SIAM Journal on Computing, 46(3), 1029--1061.
- Poloczek, M., Wang, J., & Frazier, P. (2017). Multi-information source optimization. Advances in Neural Information Processing Systems.More infoCode at https://github.com/misokg/NIPS2017
- Wu, J., Poloczek, M., Wilson, A. G., & Frazier, P. (2017). Bayesian optimization with gradients. Advances in Neural Information Processing Systems.More infoCode at https://github.com/wujian16/Cornell-MOE