Computer Science Theory Seminar
Omar Montassir
University of Chicago
Learning Predictors Robust to Adversarial Examples: Complexity and Algorithms
Abstract: In this talk, we will discuss the problem of learning an adversarially robust predictor from i.i.d. training data. That is, learning a predictor that performs well not only on future i.i.d. test instances, but also on adversarial perturbations of these instances. There has been much empirical interest in this question, and in this talk we will take a theoretical perspective and see how it leads to practically relevant insights, including: the need to depart from a (robust) empirical risk minimization approach, and thinking of what kind of accesses and reductions can allow provable learning guarantees.
Based on joint work with Steve Hanneke and Nati Srebro.
Wednesday February 16, 2022 at 4:00 PM in 636 SEO