Conditional mean embeddings as regressors - supplementary
Authors:
- Steffen GrünewälderSGSteffen Grünewälder
- Guy LeverGLGuy Lever
- Luca BaldassarreLBLuca Baldassarre
- Sam PattersonSPSam Patterson
- Arthur GrettonAGArthur Gretton
- Massimilano PontilMPMassimilano Pontil
Preprint
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^{-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.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- Kernel dimension reduction in regressionThe Annals of Statistics, 2009
- Hilbert space embeddings of conditional distributions with applications to dynamical systems2009
- Gaussian process dynamic programmingNeurocomputing, 2009
- A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse ProblemsSIAM Journal on Imaging Sciences, 2009
- VECTOR VALUED REPRODUCING KERNEL HILBERT SPACES OF INTEGRABLE FUNCTIONS AND MERCER THEOREMAnalysis and Applications, 2006
- Optimal Rates for the Regularized Least-Squares AlgorithmFoundations of Computational Mathematics, 2006
- Kernel Methods for Pattern Analysis2004
- Reproducing Kernel Hilbert Spaces in Probability and Statistics2004