Marek Petrik

Phone: (603) 862-2682
Office: Computer Science, Kingsbury Hall Rm N229, Durham, NH 03824
Marek Petrik


  • Ph.D., Computer Science, University of Massachusetts - Amherst
  • M.S., University of Massachusetts - Boston
  • M.S., Computer Science, University of Massachusetts - Amherst
  • B.S., Univerzita Komenskeho

Research Interests

  • Artificial Intelligence/Cybernetics
  • Optimization

Courses Taught

  • CS 696: Independent Study
  • CS 696W: Independent Study\Honors
  • CS 750/850: Machine Learning
  • CS 780/880: Top/Machine Learning
  • CS 950: Advanced Machine Learning
  • CS 980: Topics/Machine Learning
  • CS 999: Doctoral Research
  • CS/MATH 757/857/757/857: Mathematical Optimization
  • INCO 590: Rsrch Exp/Computer Science
  • MATH 757: Mathematical Optimization
  • MATH 857: Mathematical Optimization

Selected Publications

Iancu, D. A., Petrik, M., & Subramanian, D. (2015). Tight Approximations of Dynamic Risk Measures. Mathematics of Operations Research, 40(3), 655-682. doi:10.1287/moor.2014.0689

Buckley, S., Ettl, M., Jain, P., Luss, R., Petrik, M., Ravi, R. K., & Venkatramani, C. (2014). Social media and customer behavior analytics for personalized customer engagements. IBM Journal of Research and Development, 58(5/6), 7:1-7:12. doi:10.1147/jrd.2014.2344515

Dhurandhar, A., & Petrik, M. (2014). Efficient and accurate methods for updating generalized linear models with multiple feature additions. Journal of Machine Learning Research, 15, 2607-2627. Retrieved from

Petrik, M., & Zilberstein, S. (2011). Robust approximate bilinear programming for value function approximation. Journal of Machine Learning Research, 12, 3027-3063. Retrieved from

Johns, J., Petrik, M., & Mahadevan, S. (2009). Hybrid least-squares algorithms for approximate policy evaluation. Machine Learning, 76(2-3), 243-256. doi:10.1007/s10994-009-5128-4

Petrik, M., & Zilberstein, S. (2009). A bilinear programming approach for multiagent planning. Journal of Artificial Intelligence Research, 35, 235-274.

Petrik, M., & Zilberstein, S. (2007). Learning parallel portfolios of algorithms. Annals of Mathematics and Artificial Intelligence, 48(1-2), 85-106. doi:10.1007/s10472-007-9050-9

Petrik, M. (2005). Learning parallel portfolios of algorithms. Unknown Journal, 1-10.

Liu, B., Gemp, I., Ghavamzadeh, M., Liu, J., Mahadevan, S., & Petrik, M. (n.d.). Proximal Gradient Temporal Difference Learning: Stable Reinforcement Learning with Polynomial Sample Complexity. Journal of Artificial Intelligence Research, 63, 461-494. doi:10.1613/jair.1.11251

Most Cited Publications