STA 290 Seminar: Edgar Dobriban

Event Date

remotely presented via Zoom

Speaker: Edgar Dobriban (Assistant Professor, Statistics, University of Pennsylvania)

Title: "On the statistical foundations of adversarially robust learning"

Abstract: Robustness has long been viewed as an important desired property of statistical methods. More recently, it has been recognized that complex prediction models such as deep neural nets can be highly vulnerable to adversarially chosen perturbations of their outputs at test time. This area, termed adversarial robustness, has garnered an extraordinary level of attention in the machine learning community over the last few years. However, little is known about the most basic
statistical questions. In this talk, I will present answers to some of them. In particular, I will show how class imbalance has a crucial effect, and leads to unavoidable tradeoffs between robustness and accuracy, even in the limit of infinite data (i.e., for the Bayes error). I will also show other results, some of them involving novel applications of results from robust isoperimetry (Cianchi et al, 2011).

This is joint work with Hamed Hassani, David Hong, and Alex Robey.

About the speaker: Edgar Dobriban is currently an Assistant Professor of Statistics at the Wharton School of the University of Pennsylvania. He received his PhD from Stanford University in 2017. His main research interests are high dimensional statistics and foundations of modern machine learning, including deep learning.

Seminar Date/Time: Thursday January 14, 4:10pm

This seminar will be delivered remotely via Zoom. To access the Zoom meeting for this seminar, please contact the instructor Xiucai Ding ( or Pete Scully ( for the meeting ID and password, stating your affiliation.