6 citations · 11 across the 2 of their papers we have counts for
3 papers
stat.ML2022★ 5 cited
Differentially Private Estimation of Heterogeneous Causal Effects
Fengshi Niu, Harsha Nori, Brian Quistorff +3
Estimating heterogeneous treatment effects in domains such as healthcare or social science often involves sensitive data where protecting privacy is important. We introduce a gener…
cs.LG2021★ 6 cited
Accuracy, Interpretability, and Differential Privacy via Explainable Boosting
Harsha Nori, Rich Caruana, Zhiqi Bu +2
We show that adding differential privacy to Explainable Boosting Machines (EBMs), a recent method for training interpretable ML models, yields state-of-the-art accuracy while prote…
cs.LG2019
InterpretML: A Unified Framework for Machine Learning Interpretability
Harsha Nori, Samuel Jenkins, Paul Koch +1
InterpretML is an open-source Python package which exposes machine learning interpretability algorithms to practitioners and researchers. InterpretML exposes two types of interpret…