1.5k citations · 4.7k across the 24 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
cs.LG2021★ 4 cited
Editing a classifier by rewriting its prediction rules
Shibani Santurkar, Dimitris Tsipras, Mahalaxmi Elango +3
We present a methodology for modifying the behavior of a classifier by directly rewriting its prediction rules. Our approach requires virtually no additional data collection and ca…
cs.LG2021
Combining Diverse Feature Priors
Saachi Jain, Dimitris Tsipras, Aleksander Madry
To improve model generalization, model designers often restrict the features that their models use, either implicitly or explicitly. In this work, we explore the design space of le…