Corpus ID: 22775291

Density Estimation in Infinite Dimensional Exponential Families

@article{Sriperumbudur2017DensityEI,
  title={Density Estimation in Infinite Dimensional Exponential Families},
  author={Bharath K. Sriperumbudur and Kenji Fukumizu and Arthur Gretton and Aapo Hyv{\"a}rinen and Revant Kumar},
  journal={J. Mach. Learn. Res.},
  year={2017},
  volume={18},
  pages={57:1-57:59}
}
  • Bharath K. Sriperumbudur, Kenji Fukumizu, +2 authors Revant Kumar
  • Published 2017
  • Mathematics, Computer Science
  • J. Mach. Learn. Res.
  • In this paper, we consider an infinite dimensional exponential family, $\mathcal{P}$ of probability densities, which are parametrized by functions in a reproducing kernel Hilbert space, $H$ and show it to be quite rich in the sense that a broad class of densities on $\mathbb{R}^d$ can be approximated arbitrarily well in Kullback-Leibler (KL) divergence by elements in $\mathcal{P}$. The main goal of the paper is to estimate an unknown density, $p_0$ through an element in $\mathcal{P}$. Standard… CONTINUE READING

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 68 CITATIONS

    Exponential Series Approaches for Nonparametric Graphical Models

    VIEW 2 EXCERPTS
    CITES METHODS

    Fisher Efficient Inference of Intractable Models

    VIEW 1 EXCERPT
    CITES METHODS

    Efficient and principled score estimation

    VIEW 9 EXCERPTS
    CITES RESULTS, METHODS & BACKGROUND

    A Spectral Approach to Gradient Estimation for Implicit Distributions

    VIEW 2 EXCERPTS
    CITES BACKGROUND & METHODS

    FILTER CITATIONS BY YEAR

    2015
    2020

    CITATION STATISTICS

    • 5 Highly Influenced Citations

    • Averaged 14 Citations per year from 2018 through 2020

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 42 REFERENCES

    Estimation of Non-Normalized Statistical Models by Score Matching

    VIEW 14 EXCERPTS

    On regularization algorithms in learning theory

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Optimal Rates for the Regularized Least-Squares Algorithm

    VIEW 2 EXCERPTS