← Search

Kivanc Kose

1 accepted papers

2023

SmoothHess: ReLU Network Feature Interactions via Stein's Lemma

NeurIPS 2023poster

Several recent methods for interpretability model feature interactions by looking at the Hessian of a neural network. This poses a challenge for ReLU networks, which are piecewise-linear and thus have a zero Hessian almost everywhere. We propose SmoothHess, a method of estimating second-order intera…