Corpus ID: 211069493

A Measure-Theoretic Approach to Kernel Conditional Mean Embeddings

@article{Park2020AMA,
  title={A Measure-Theoretic Approach to Kernel Conditional Mean Embeddings},
  author={Jun-Hyung Park and Krikamol Muandet},
  journal={ArXiv},
  year={2020},
  volume={abs/2002.03689}
}
  • Jun-Hyung Park, Krikamol Muandet
  • Published in ArXiv 2020
  • Mathematics, Computer Science
  • 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… CONTINUE READING

    Figures and Topics from this paper.

    Citations

    Publications citing this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 55 REFERENCES

    Probability and Stochastics, volume 261

    • E. Çınlar
    • Springer Science & Business Media.
    • 2011
    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Operator-valued Kernels for Learning from Functional Response Data

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    A Hilbert Space Embedding for Distributions

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Conditional Generative Moment-Matching Networks

    VIEW 1 EXCERPT
    HIGHLY INFLUENTIAL

    Kernel Bayes' rule: Bayesian inference with positive definite kernels

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL