Dr. Peter Bartlett – Professor, Department of Statistics at University of California, Berkeley

CANCELLED

Title: Benign Overfitting

Abstract: Deep learning has revealed some major surprises from the perspective of statistical complexity: even without any explicit
effort to control model complexity, these methods find prediction rules that give a near-perfect fit to noisy training data and yet
exhibit excellent prediction performance in practice. This talk reviews recent work on methods that predict accurately in
probabilistic settings despite fitting too well to training data. We see how benign overfitting can occur with sufficient
overparameterization in regression and classification problems, but it leads to sensitivity to adversarial examples.
Based on joint work with Phil Long, Gabor Lugosi, Alex Tsigler, Niladri Chatterji, Spencer Frei, Wei Hu, Nati Srebro, and Gal Vardi.

Coffee served before lecture at 3pm