We formalize coherence --a requirement that erroneous predictions, within a slice, should be wrong for the same reason --as a key property that any slice discovery method should satisfy.

Neural Information Processing Systems http://nips.cc/

We use 9 datasets and pre-trained models provided in Chen et al. (2019b), which can be downloaded Methods on the bottom-left corner are better. For completeness we include verification results (Chen et al., 2019b; Wang et al., 2020) in

We have 2 large datasets, HIGGS and Bosch (see reply to[R3]-1)). Table B highlights our differences.3) Motivation: We provide a strong attack as a tool for evaluating the9 robustnessoftreebasedmodels. MILP uses a thin wrapper around the Gurobi Solver.

Inparticular,forany function in a classC of bounded VC dimension, we guarantee a low test error rate and a low rejection ratewith respect toP. Our algorithm is efficient given an Empirical Risk Minimizer (ERM) forC.