2 papers
cs.LG2021
Provably Robust Model-Centric Explanations for Critical Decision-Making
Cecilia G. Morales, Nicholas Gisolfi, Robert Edman +2
We recommend using a model-centric, Boolean Satisfiability (SAT) formalism to obtain useful explanations of trained model behavior, different and complementary to what can be glean…
stat.ML2017
Scaling Active Search using Linear Similarity Functions
Sibi Venkatesan, James K. Miller, Jeff Schneider +1
Active Search has become an increasingly useful tool in information retrieval problems where the goal is to discover as many target elements as possible using only limited label qu…