FastSHAP: Real-Time Shapley Value Estimation

3 code implementations • ICLR 2022 • Neil Jethani, Mukund Sudarshan, Ian Covert, Su-In Lee, Rajesh Ranganath

Shapley values are widely used to explain black-box models, but they are costly to calculate because they require many model evaluations.

Have We Learned to Explain?: How Interpretability Methods Can Learn to Encode Predictions in their Interpretations

1 code implementation • 2 Mar 2021 • Neil Jethani, Mukund Sudarshan, Yindalon Aphinyanaphongs, Rajesh Ranganath

While the need for interpretable machine learning has been established, many common approaches are slow, lack fidelity, or hard to evaluate.

Interpretable Machine Learning

Deep Direct Likelihood Knockoffs

1 code implementation • NeurIPS 2020 • Mukund Sudarshan, Wesley Tansey, Rajesh Ranganath

Predictive modeling often uses black box machine learning methods, such as deep neural networks, to achieve state-of-the-art performance.

Model-Agnostic Feature Selection with Additional Mutual Information

no code implementations • 25 Sep 2019 • Mukund Sudarshan, Aahlad Manas Puli, Lakshmi Subramanian, Sriram Sankararaman, Rajesh Ranganath

We show that f-divergences provide a broad class of proper test statistics.

Feature Importance Image Classification