Timezone: »

Editing a classifier by rewriting its prediction rules
Shibani Santurkar · Dimitris Tsipras · Mahalaxmi Elango · David Bau · Antonio Torralba · Aleksander Madry

Tue Dec 07 08:30 AM -- 10:00 AM (PST) @

We propose a methodology for modifying the behavior of a classifier by directly rewriting its prediction rules. Our method requires virtually no additional data collection and can be applied to a variety of settings, including adapting a model to new environments, and modifying it to ignore spurious features.

Author Information

Shibani Santurkar (MIT)
Dimitris Tsipras (Stanford)
Mahalaxmi Elango (Massachusetts Institute of Technology)
David Bau (Massachusetts Institute of Technology)
Antonio Torralba (Massachusetts Institute of Technology)
Aleksander Madry (MIT)

Aleksander Madry is the NBX Associate Professor of Computer Science in the MIT EECS Department and a principal investigator in the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL). He received his PhD from MIT in 2011 and, prior to joining the MIT faculty, he spent some time at Microsoft Research New England and on the faculty of EPFL. Aleksander's research interests span algorithms, continuous optimization, science of deep learning and understanding machine learning from a robustness perspective. His work has been recognized with a number of awards, including an NSF CAREER Award, an Alfred P. Sloan Research Fellowship, an ACM Doctoral Dissertation Award Honorable Mention, and 2018 Presburger Award.

More from the Same Authors