Thursday September 1

Thursday, September 1, Robust Optimization

Workshop Chair: Andy Sun

Time: 9:00 – 12:00
Speaker: Andy Sun
Title: Tutorial on Robust Optimization

Time: 12:00 – 14:00 – Lunch

Time: 14:00 – 15:00
Speaker: Huan Xu
Title: All Learning is Robust
Abstract: Controlling overfitting is a long standing topic of study in machine learning. Regularization is a commonly used technique to control overfitting where a penalty is added to the cost function (typically the classification or regression error). The success of regularization in a host of different algorithms is usually interpreted as coming from penalizing the complexity of the resulting decision rules favoring simple rules. In this talk we propose a different perspective to learning base on robust optimization. That is, assuming that each sample corrupted by a certain disturbance, we find the best decision under the most adversarial perturbation. We show that a special choice of the perturbation exactly recovers the solution obtained by penalizing complexity via regularization. Both Support Vector Machines and Lasso can be re-derived from a robust optimization perspective. The equivalence relationship between regularization and robustness gives a physical interpretation of the regularization process. Moreover, it helps us explain from a robustness point of view why support vector machines are statistically consistent, and why Lasso produces sparse solutions. Generalizing these results we use the robustness perspective to derive new algorithms in new domains that have both favorable statistical and computational properties. We finally argue that robustness is a necessary and sufficient condition for consistency of learning algorithms and in fact every useful learning algorithm must possess some robustness properties.

Time: 16:00 – 17:00
Speaker: Andy Sun
Title: Robust optimization in Energy Systems
Abstract: I will present some recent work on modeling uncertainty in the electric energy systems concerning renewable integration and flexible demand. The talk will discuss two-stage and multistage robust optimization models for the unit commitment problem, the economic dispatch problem, and a long-term planning problem. Affine decision rules and constraint/column generation methods are developed for the solution of these challenging large-scale optimization problems.