`

Timezone: »

 
Poster
A Measure-Theoretic Approach to Kernel Conditional Mean Embeddings
Junhyung Park · Krikamol Muandet

Wed Dec 09 09:00 AM -- 11:00 AM (PST) @ Poster Session 3 #986
in Poster Session 4 »

We present a new operator-free, measure-theoretic approach to 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 treatment, and depends on strong assumptions that hinder its analysis. Our approach 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 with improved convergence rates. 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.

[Paper]

Author Information

Junhyung Park (MPI for Intelligent Systems, Tübingen)
Krikamol Muandet (Max Planck Institute for Intelligent Systems)

More from the Same Authors