Timezone: »

 
Spotlight
An Asymptotic Test for Conditional Independence using Analytic Kernel Embeddings
Meyer Scetbon · Laurent Meunier · Yaniv Romano

Thu Jul 21 08:40 AM -- 08:45 AM (PDT) @ Room 327 - 329
in MISC/Deep Learning »

We propose a new conditional dependence measure and a statistical test for conditional independence. The measure is based on the difference between analytic kernel embeddings of two well-suited distributions evaluated at a finite set of locations. We obtain its asymptotic distribution under the null hypothesis of conditional independence and design a consistent statistical test from it. We conduct a series of experiments showing that our new test outperforms state-of-the-art methods both in terms of type-I and type-II errors even in the high dimensional setting.

Keywords: MISC: Causality · MISC: Kernel methods

Author Information

Meyer Scetbon (CREST, ENSAE)
Laurent Meunier (Dauphine University - FAIR Paris)
Yaniv Romano (Technion---Israel Institute of Technology)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors