Search Results for author:
Found 3 papers, 0 papers with code
Learning Exceptional Subgroups by End-to-End Maximizing KL-divergence
Finding and describing sub-populations that are exceptional regarding a target property has important applications in many scientific disciplines, from identifying disadvantaged demographic groups in census data to finding conductive molecules within gold nanoparticles.
Finding Interpretable Class-Specific Patterns through Efficient Neural Search
Discovering patterns in data that best describe the differences between classes allows to hypothesize and reason about class-specific mechanisms.
On Fragile Features and Batch Normalization in Adversarial Training
In order to shed light on the role of BN in adversarial training, we investigate to what extent the expressiveness of BN can be used to robustify fragile features in comparison to random features.
