- This event has passed.
ASSET Seminar: “Building a Foundation for Trustworthy Machine Learning” (Elan Rosenfeld, Carnegie Mellon University)
April 3 at 12:00 PM - 1:30 PM
ABSTRACT:
Using a case study of invariant prediction, we first highlight the importance of formally specifying the space of adverse events we’d like to handle at deployment time. This provides a mathematical framework for analyzing, comparing, and improving the robustness of ML algorithms. Then, we explore how careful experimental probing of these methods’ failures leads to a deeper understanding of the underlying causes, and how these insights can inform the design of new methods with more reliable real-world behavior. We conclude with a brief summary of other past and ongoing works towards provably secure ML, including a scalable framework which enables certified robustness to adversarial train- and test-time attacks.
ZOOM LINK (if unable to attend in-person): https://upenn.zoom.us/j/95678270617
Elan Rosenfeld
Ph.D. Student
Elan Rosenfeld is a PhD student in the Machine Learning Department at CMU, advised by Andrej Risteski and Pradeep Ravikumar. His research focuses on understanding, quantifying, and improving the robustness and trustworthiness of machine learning systems.