Better Solutions From Inaccurate Models
It is very important in many application domains to compute good solutions from inaccurate models. Models in machine learning are inaccurate because they both simplify reality and are based on imperfect data. Robust optimization has emerged as a very powerful methodology for reducing solution sensitivity to model errors. In the first part of the talk, I will describe how robust optimization can mitigate data limitations in planning a large-scale disaster recovery operation. In the second part of the talk, I will discuss a novel use of robustness to substantially reducing error due to model simplification in reinforcement learning and large-scale regression.
Marek Petrik is a Research Staff Member at the Business Services and Mathematical Sciences Department at IBM's T.J. Watson Research Center. He received his Ph.D. in Computer Science from the University of Massachusetts, Amherst. His research focuses on machine learning and optimization with a special interest in robust and risk-averse optimization and stochastic sequential optimization problems. He has worked on applications such as agricultural and environmental monitoring, supply chain optimization, revenue management, and online recommendations.