People

Omar Montasser is an Assistant Professor at Yale in the department of Statistics and Data Science. His research broadly explores theory and foundations of machine learning. Recently, his research has focused on the problem of learning predictors robust against adversarial examples, exploring what robustness properties can we hope to guarantee and how to guarantee them. His work has been recognized by a best student paper award at COLT (2019). Prior to joining Yale, Montasser was a FODSI-Simons postdoctoral fellow at UC Berkeley. He received his Ph.D. from the Toyota Technological Institute at Chicago in 2023, and his B.S. from Penn State in 2017.

What do you do with Data Science?

My research broadly explores theory and foundations of machine learning. Recently, my research has focused on the problem of learning predictors robust against adversarial examples, exploring what robustness properties can we hope to guarantee and understanding how to guarantee them. A central goal of my research is to develop rigorous learning guarantees for modern machine learning challenges that arise in real-world applications. Selected publications: Boosting Barely Robust Learners: A New Perspective on Adversarial Robustness Avrim Blum, Omar Montasser, Greg Shakhnarovich, Hongyang Zhang NeurIPS, 2022. VC Classes are Adversarially Robustly Learnable, but Only Improperly Omar Montasser, Steve Hanneke, and Nathan Srebro COLT, 2019.

Edit profile