TY - JOUR

T1 - Density estimation in infinite dimensional exponential families

AU - Sriperumbudur, Bharath

AU - Fukumizu, Kenji

AU - Gretton, Arthur

AU - Hyvärinen, Aapo

AU - Kumar, Revant

N1 - Publisher Copyright:
© 2017 Bharath Sriperumbudur, Kenji Fukumizu, Arthur Gretton, Aapo Hyvärinen and Revant Kumar.

PY - 2017/7/1

Y1 - 2017/7/1

N2 - In this paper, we consider an infinite dimensional exponential family 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 Rd can be approximated arbitrarily well in Kullback-Leibler (KL) divergence by elements in P. Motivated by this approximation property, the paper addresses the question of estimating an unknown density po through an element in P. Standard techniques like maximum likelihood estimation (MLE) or pseudo MLE (based on the method of sieves), which are based on minimizing the KL divergence between po and P, do not yield practically useful estimators because of their inability to efficiently handle the log-partition function. We propose an estimator pn based on minimizing the Fisher divergence, J(po||p) between po and p ϵ P, which involves solving a simple finite-dimensional linear system. When po ϵ P, we show that the pro-posed estimator is consistent, and provide a convergence rate of n-min {2/3, 2β+1/2β+2} in Fisher divergence under the smoothness assumption that log po ϵ 72. (Cβ) for some β ≥ 0, where C is a certain Hilbert-Schmidt operator on H and R(Cβ) denotes the image of Cβ. We also investigate the misspecified case of po ϵ P and show that J(po||pn) → infpϵP J(po||p) as n → ∞, and provide a rate for this convergence under a similar smoothness condition as above. Through numerical simulations we demonstrate that the proposed estimator outperforms the non-parametric kernel density estimator, and that the advantage of the proposed estimator grows as d increases.

AB - In this paper, we consider an infinite dimensional exponential family 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 Rd can be approximated arbitrarily well in Kullback-Leibler (KL) divergence by elements in P. Motivated by this approximation property, the paper addresses the question of estimating an unknown density po through an element in P. Standard techniques like maximum likelihood estimation (MLE) or pseudo MLE (based on the method of sieves), which are based on minimizing the KL divergence between po and P, do not yield practically useful estimators because of their inability to efficiently handle the log-partition function. We propose an estimator pn based on minimizing the Fisher divergence, J(po||p) between po and p ϵ P, which involves solving a simple finite-dimensional linear system. When po ϵ P, we show that the pro-posed estimator is consistent, and provide a convergence rate of n-min {2/3, 2β+1/2β+2} in Fisher divergence under the smoothness assumption that log po ϵ 72. (Cβ) for some β ≥ 0, where C is a certain Hilbert-Schmidt operator on H and R(Cβ) denotes the image of Cβ. We also investigate the misspecified case of po ϵ P and show that J(po||pn) → infpϵP J(po||p) as n → ∞, and provide a rate for this convergence under a similar smoothness condition as above. Through numerical simulations we demonstrate that the proposed estimator outperforms the non-parametric kernel density estimator, and that the advantage of the proposed estimator grows as d increases.

UR - http://www.scopus.com/inward/record.url?scp=85025452858&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85025452858&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:85025452858

VL - 18

JO - Journal of Machine Learning Research

JF - Journal of Machine Learning Research

SN - 1532-4435

ER -