Papers › Density Estimation in Infinite Dimensional Exponential Families

Density Estimation in Infinite Dimensional Exponential Families

12 Dec 2013arXiv:1312.3516archive 2025-07-28

Bharath Sriperumbudur, Kenji Fukumizu, Arthur Gretton, Aapo Hyvärinen, Revant Kumar

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. The main goal of the paper is to estimate an unknown density, p₀ 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 p₀ and 𝒫, do not yield practically useful estimators because of their inability to efficiently handle the log-partition function. Instead, we propose an estimator, p̂ₙ based on minimizing the Fisher divergence, J(p₀‖p) between p₀ and p∈𝒫, which involves solving a simple finite-dimensional linear system. When p₀∈𝒫, we show that the proposed estimator is consistent, and provide a convergence rate of n^(-min2/3,(2β+1)/(2β+2)) in Fisher divergence under the smoothness assumption that logp₀∈ℛ(C^β) for some β≥0, where C is a certain Hilbert-Schmidt operator on H and ℛ(C^β) denotes the image of C^β. We also investigate the misspecified case of p₀∉𝒫 and show that J(p₀‖p̂ₙ)→inf_(p∈𝒫)J(p₀‖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 with the proposed estimator grows as d increases.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

karlnapf/kernel_exp_family mentioned on GitHubBSD-3-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Gradient-free Hamiltonian Monte Carlo with Efficient Kernel Exponential Families (arXiv:1506.02564; that paper's own run record: 21 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 0 violated, 21 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Density Estimation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections