Designing Differentially Private Estimators in High Dimensions

1 code implementation • 2 Jun 2020 • Aditya Dhar, Jason Huang

This yields a computationally tractable algorithm for differentially private mean estimation in high dimensions with dimension-independent privacy loss.

Vocal Bursts Intensity Prediction

Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias

1 code implementation • 26 Apr 2020 • Jesse Vig, Sebastian Gehrmann, Yonatan Belinkov, Sharon Qian, Daniel Nevo, Simas Sakenis, Jason Huang, Yaron Singer, Stuart Shieber

Common methods for interpreting neural models in natural language processing typically examine either their structure or their behavior, but not both.