# Density Estimation in Infinite Dimensional Exponential Families

arXiv: https://arxiv.org/abs/1312.3516 · HTML: https://mlsanity.com/paper/1312.3516/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Dec 2013.

## Built on by (most cited first, 30 of 42)

- [Optimal score estimation via empirical Bayes smoothing](https://mlsanity.com/paper/2402.07747/) (2024)
- [Nonlinear Invariant Risk Minimization: A Causal Approach](https://mlsanity.com/paper/2102.12353/) (2021)
- [Causal Representation Learning Made Identifiable by Grouping of Observational Variables](https://mlsanity.com/paper/2310.15709/) (2023)
- [PSD Representations for Effective Probability Models](https://mlsanity.com/paper/2106.16116/) (2021)
- [Causal Balancing for Domain Generalization](https://mlsanity.com/paper/2206.05263/) (2022)
- [Robust and Scalable Bayesian Online Changepoint Detection](https://mlsanity.com/paper/2302.04759/) (2023)
- [Provable benefits of annealing for estimating normalizing constants: Importance Sampling, Noise-Contrastive Estimation, and beyond](https://mlsanity.com/paper/2310.03902/) (2023)
- [A Computationally Efficient Method for Learning Exponential Family Distributions](https://mlsanity.com/paper/2110.15397/) (2021)
- [Sampling Multimodal Distributions with the Vanilla Score: Benefits of Data-Based Initialization](https://mlsanity.com/paper/2310.01762/) (2023)
- [The Score-Difference Flow for Implicit Generative Modeling](https://mlsanity.com/paper/2304.12906/) (2023)
- [Differentiable Neural Networks with RePU Activation: with Applications to Score Estimation and Isotonic Regression](https://mlsanity.com/paper/2305.00608/) (2023)
- [Algorithmic Differentiation for Automated Modeling of Machine Learned Force Fields](https://mlsanity.com/paper/2208.12104/) (2022)
- [Neural Operator Variational Inference based on Regularized Stein Discrepancy for Deep Gaussian Processes](https://mlsanity.com/paper/2309.12658/) (2023)
- [Exponential Family Model-Based Reinforcement Learning via Score Matching](https://mlsanity.com/paper/2112.14195/) (2021)
- [Active Slices for Sliced Stein Discrepancy](https://mlsanity.com/paper/2102.03159/) (2021)
- [Do autoencoders need a bottleneck for anomaly detection?](https://mlsanity.com/paper/2202.12637/) (2022)
- [Nonparametric Automatic Differentiation Variational Inference with Spline Approximation](https://mlsanity.com/paper/2403.06302/) (2024)
- [Stein's method for marginals on large graphical models](https://mlsanity.com/paper/2410.11771/) (2024)
- [Conditionally Strongly Log-Concave Generative Models](https://mlsanity.com/paper/2306.00181/) (2023)
- [Sobolev Space Regularised Pre Density Models](https://mlsanity.com/paper/2307.13763/) (2023)
- [On Computationally Efficient Learning of Exponential Family Distributions](https://mlsanity.com/paper/2309.06413/) (2023)
- [Avoiding subtraction and division of stochastic signals using normalizing flows: NFdeconvolve](https://mlsanity.com/paper/2501.08288/) (2025)
- [Learning Theory for Kernel Bilevel Optimization](https://mlsanity.com/paper/2502.08457/) (2025)
- [Fast and Scalable Score-Based Kernel Calibration Tests](https://mlsanity.com/paper/2510.14711/) (2025)
- [Denoising Score Matching with Random Fourier Features](https://mlsanity.com/paper/2101.05239/) (2021)
- [Strong posterior contraction rates via Wasserstein dynamics](https://mlsanity.com/paper/2203.10754/) (2022)
- [Bayes Hilbert Spaces for Posterior Approximation](https://mlsanity.com/paper/2304.09053/) (2023)
- [Robust Estimation for Kernel Exponential Families with Smoothed Total Variation Distances](https://mlsanity.com/paper/2410.20760/) (2024)
- [Uniform Convergence Beyond Glivenko-Cantelli](https://mlsanity.com/paper/2510.21506/) (2025)
- [Provably Reliable Classifier Guidance via Cross-Entropy Control](https://mlsanity.com/paper/2601.21200/) (2026)

## Abstract (arXiv)

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, hatpn based on minimizing the Fisher divergence, J(p0Vert 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^-minleftfrac23,frac2β+12β+2right in Fisher divergence under the smoothness assumption that log p0∈R(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 p0notinP and show that J(p0Verthatpn)rightarrow infp∈PJ(p0Vert p) as nrightarrow∞, 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.