16 citations · 20 across the 2 of their papers we have counts for
5 papers
Oblique Decision Trees from Derivatives of ReLU Networks
Guang-He Lee, Tommi S. Jaakkola
We show how neural models can be used to realize piece-wise constant functions such as decision trees. The proposed architecture, which we call locally constant networks, builds on…
Towards Robust, Locally Linear Deep Networks
Guang-He Lee, David Alvarez-Melis, Tommi S. Jaakkola
Deep networks realize complex mappings that are often understood by their locally linear behavior at or around points of interest. For example, we use the derivative of the mapping…
Tight Certificates of Adversarial Robustness for Randomly Smoothed Classifiers
Guang-He Lee, Yang Yuan, Shiyu Chang +1
Strong theoretical guarantees of robustness can be given for ensembles of classifiers generated by input randomization. Specifically, an bounded adversary cannot alter the…
Functional Transparency for Structured Data: a Game-Theoretic Approach
Guang-He Lee, Wengong Jin, David Alvarez-Melis +1
We provide a new approach to training neural models to exhibit transparency in a well-defined, functional manner. Our approach naturally operates over structured data and tailors t…
Game-Theoretic Interpretability for Temporal Modeling
Guang-He Lee, David Alvarez-Melis, Tommi S. Jaakkola
Interpretability has arisen as a key desideratum of machine learning models alongside performance. Approaches so far have been primarily concerned with fixed dimensional inputs emp…