A Measure-Theoretic Approach to Kernel Conditional Mean Embeddings

NeurIPS 2020

A Measure-Theoretic Approach to Kernel Conditional Mean Embeddings

Dec 06, 2020
|
39 views
|
Details
We present a new operator-free, measure-theoretic definition of the conditional mean embedding as a random variable taking values in a reproducing kernel Hilbert space. While the kernel mean embedding of marginal distributions has been defined rigorously, the existing operator-based approach of the conditional version lacks a rigorous definition, and depends on strong assumptions that hinder its analysis. Our definition does not impose any of the assumptions that the operator-based counterpart requires. We derive a natural regression interpretation to obtain empirical estimates, and provide a thorough analysis of its properties, including universal consistency. As natural by-products, we obtain the conditional analogues of the Maximum Mean Discrepancy and Hilbert-Schmidt Independence Criterion, and demonstrate their behaviour via simulations. Speakers: Junhyung Park, Krikamol Muandet

Comments
loading...