no code implementations • 8 Jun 2020 • Frederick Liu, Amir Najmi, Mukund Sundararajan
There is a set of data augmentation techniques that ablate parts of the input at random.
no code implementations • ICML 2020 • Mukund Sundararajan, Amir Najmi
In this paper, we use the axiomatic approach to study the differences between some of the many operationalizations of the Shapley value for attribution, and propose a technique called Baseline Shapley (BShap) that is backed by a proper uniqueness result.
no code implementations • NeurIPS 2014 • Stefan Wager, Nick Chamandy, Omkar Muralidharan, Amir Najmi
A predictor that is deployed in a live production system may perturb the features it uses to make predictions.