Differentially Private Conditional Independence Testing

arXiv:2306.06721v3 Announce Type: replace-cross
Abstract: Conditional independence (CI) tests are widely used in statistical data analysis, e.g., they are the building block of many algorithms for causal graph discovery. The goal of a CI test is to accept or reject the null hypothesis that $X \perp \!\!\! \perp Y \mid Z$, where $X \in \mathbb{R}, Y \in \mathbb{R}, Z \in \mathbb{R}^d$. In this work, we investigate conditional independence testing under the constraint of differential privacy. We design two private CI …

abstract algorithms analysis arxiv block building causal cs.cr cs.lg data data analysis discovery graph hypothesis null statistical stat.ml test testing tests type