CyLab Seminar: Andrew Ilyas

Speaker: Andrew Ilyas Assistant Professor, Electrical and Computer Engineering & Software and Societal Systems Carnegie Mellon University Talk Title: Talk title coming soon Abstract: Abstract coming soon Bio: Andrew Ilyas is an assistant professor at CMU. Previously, he was a Stein Fellow at Stanford Statistics and a Ph.D. student MIT, where he was fortunate to be advised by Costis DaskalakisOpens in new window and Aleksander MadryOpens in new window and supported by an Open Philanthropy AI FellowshipOpens in new window. Ilyas attended MIT for undergrad, majoring in CS and in Math. Outside of research, I enjoy playing soccer and table tennis. Ilyas’s goal is to uncover general principles that describe and predict the behavior of ML systems—ideally enabling predictably reliable future systems. This goal entails combining statistical tools with large-scale experiments to precisely understand the ML “pipeline,” from training data (and the way we collect it), to learning algorithms, to deployment. He also likes thinking broadly about (human) trust in AI systems.