Computer Science Seminar: Andrew Ilyas

Description

Andrew Ilyas, a doctoral student in computer science at the Massachusetts Institute of Technology, will give a talk titled "Making Machine Learning Predictably Reliable" for the Department of Computer Science.

This is a hybrid event; to attend virtually, the Zoom link is on the event page.

Abstract:

Despite machine learning models' impressive performance, training and deploying them is currently a somewhat messy endeavor. But does it have to be? In this talk, Andrew Ilyas overviews his work on making ML "predictably reliable"—enabling developers to know when their models will work, when they will fail, and why. To begin, he uses a case study of adversarial inputs to show that human intuition can be a poor predictor of how ML models operate. Motivated by this, he presents a line of work that aims to develop a precise understanding of the ML pipeline, combining statistical tools with large-scale experiments to characterize the role of each individual design choice: from how to collect data, to what dataset to train on, to what learning algorithm to use.