Home > Research > Publications & Outputs > Conditional mean embeddings as regressors

Links

View graph of relations

Conditional mean embeddings as regressors

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published
Close
Publication date2012
Host publicationProceedings of the 29th International Conference on Machine Learning, Edinburgh, Scotland, 2012
<mark>Original language</mark>English

Abstract

We demonstrate an equivalence between reproducing kernel Hilbert space (RKHS) embeddings of conditional distributions and vector-valued regressors.
This connection introduces a natural regularized loss function which the RKHS embeddings minimise, providing an intuitive understanding of the embeddings and a justification for their use. Furthermore, the equivalence allows the application of vector-valued regression methods and results to the problem of learning conditional distributions. Using this link we derive a sparse version of the embedding by considering alternative formulations. Further, by applying
convergence results for vector-valued regression to the embedding problem we derive minimax convergence rates which are O(log(n)=n) – compared to current state of the art rates of O(n&#x100000;1=4) – and are valid under milder and more
intuitive assumptions. These minimax upper rates coincide with lower rates up to a logarithmic factor, showing that the embedding method achieves nearly optimal rates. We study our sparse embedding algorithm in a reinforcement
learning task where the algorithm shows significant improvement in sparsity over an incomplete Cholesky decomposition.