# Density estimation

Especially non- or semiparametrically

June 6, 2016 — October 16, 2019

convolution
density
functional analysis
nonparametric
probability
statistics

A statistical estimation problem where you are not trying to estimate a function of a distribution of random observations, but the distribution itself. In a sense, all of statistics implicitly does density estimation, but this is often instrumental in the course of discovering the some actual parameter of interest. (Although maybe you interest in Bayesian statistics and you care a ;lot about the shape of the posterior density in particular.)

So, estimating distributions nonparametrically is not too weird a function approximation problem. We wish to find a function a density function $$f:\mathcal{X}\to\mathbb{R}$$ such that $$\int_{\mathcal{X}}f(x)dx=1$$ and $$\forall x \in \mathcal{X},f(x)\geq 0$$.

We might set ourselves different loss functions than usual in statistical regression problems; Instead of, e.g. expected $$L_p$$ prediction error we might use a traditional function approximation $$L_p$$ loss, or a probability divergence measure.

The most common density estimate, that we use implicitly all the time, is to not work with densities as such but distributions. We take the empirical distribution as a distribution estimate; that is, taking the data as a model for itself. This has various non-useful features such as being rough and rather hard to visualise as a density.

Question: When would I actually want to estimate, specifically, a density?

Visualisation, sure. Nonparametric regression without any better ideas. As a latent parameters in a deep probabilistic model.

What about non-parametric conditional density estimation? Are there any general ways to do this?

## 1 Divergence measures/contrasts

There are many choices for loss functions between densities here; any of the probability metrics will do. For reasons of tradition or convenience, when the object of interest is the density itself, certain choices dominate:

• $$L_2$$ with respect to the density over Lebesgue measure on the state space, which we call the MISE, and works out nicely for convolution kernels.
• KL-divergence. (May not do what you want if you care about performance near 0. See .)
• Hellinger distance
• Wasserstein divergences.

But having chosen the divergence you wish to minimise, you now have to choose with respect to which criterion you wish to minimise it? Minimax? in probability? In expectation? …? Every combination is a different publication. Hmf.

## 2 Minimising Expected (or whatever) MISE

This works fine for Kernel Density Estimators where it turns out just be a Wiener filter where you have to choose a bandwidth. How do you do this for other estimators, though?

## 3 Connection to point processes

There is a connection between spatial point process intensity estimation and density estimation. See Densities and intensities.

🏗

## 5 Mixture models

See mixture models.

## 6 Gaussian processes

Gaussian process can provide posterioer densities over densities somehow?

## 7 Renormalizing flow models

A.k.a. measure transport etc. Where one uses reparameterisation. 🏗

## 8 k-NN estimates

Filed here because too small to do elsewhere.

To use nearest neighbor methods, the integer k must be selected. This is similar to bandwidth selection, although here k is discrete, not continuous. K.C. Li (Annals of Statistics, 1987) showed that for the knn regression estimator under conditional homoskedasticity, it is asymptotically optimal to pick k by Mallows, Generalized CV, or CV. Andrews (Journal of Econometrics, 1991) generalized this result to the case of heteroskedasticity, and showed that CV is asymptotically optimal.

## 9 Kernel density estimators

a.k.a. kernel smoothing.

### 9.1 Fancy ones

HT Gery Geenens for a lecture he just gave on convolution kernel density estimation where he drew a parallel between additive noise in kde estimation and multiplicative noise in non-negative-valued variables.

## 10 References

Andrews. 1991. Journal of Econometrics.
Arnold, Castillo, and Sarabia. 1999. Conditional Specification of Statistical Models.
Barron, and Sheu. 1991. The Annals of Statistics.
Bashtannyk, and Hyndman. 2001. Computational Statistics & Data Analysis.
Battey, and Liu. 2013. arXiv:1308.3968 [Stat].
Berman, and Diggle. 1989. Journal of the Royal Statistical Society. Series B (Methodological).
Birgé. 2008. arXiv:0808.1416 [Math, Stat].
Bosq. 1998. Nonparametric Statistics for Stochastic Processes: Estimation and Prediction. Lecture Notes in Statistics 110.
Cox. 1965. Journal of the Royal Statistical Society: Series B (Methodological).
Cunningham, Shenoy, and Sahani. 2008. In Proceedings of the 25th International Conference on Machine Learning. ICML ’08.
Devroye, and Lugosi. 2001. Combinatorial Methods in Density Estimation. Springer Series in Statistics.
Dinh, Ho, Nguyen, et al. 2016. In NIPS.
Efromovich. 2007. The Annals of Statistics.
Eilers, and Marx. 1996. Statistical Science.
Ellis. 1991. Stochastic Processes and Their Applications.
Giesecke, Kakavand, and Mousavi. 2008. In Simulation Conference, 2008. WSC 2008. Winter.
Gu. 1993. Journal of the American Statistical Association.
Hall. 1987. The Annals of Statistics.
Hall, Racine, and Li. 2004. Journal of the American Statistical Association.
Hansen. 2004. Unpublished Manuscript.
Hasminskii, and Ibragimov. 1990. The Annals of Statistics.
Ibragimov. 2001. In Institute of Mathematical Statistics Lecture Notes - Monograph Series.
Koenker, and Mizera. 2006. Advances in Statistical Modeling and Inference.
Kooperberg, and Stone. 1991. Computational Statistics & Data Analysis.
———. 1992. Journal of Computational and Graphical Statistics.
Lee, Ge, Ma, et al. 2017. In arXiv:1702.07028 [Cs].
Lenk. 2003. Journal of Computational and Graphical Statistics.
Li. 1987. The Annals of Statistics.
Norets. 2010. The Annals of Statistics.
Panaretos, and Zemel. 2016. The Annals of Statistics.
Papangelou. 1974. Zeitschrift Für Wahrscheinlichkeitstheorie Und Verwandte Gebiete.
Reynaud-Bouret, Rivoirard, and Tuleau-Malot. 2011. Journal of Statistical Planning and Inference.
Sardy, and Tseng. 2010. Scandinavian Journal of Statistics.
Schoenberg. 2005. Journal of Statistical Planning and Inference.
Schuster, Mollenhauer, Klus, et al. 2019. arXiv:1905.11255 [Cs, Math, Stat].
Shimazaki, and Shinomoto. 2010. Journal of Computational Neuroscience.
Sriperumbudur, Fukumizu, Gretton, et al. 2017. Journal of Machine Learning Research.
Sugiyama, Takeuchi, Suzuki, et al. 2010. In International Conference on Artificial Intelligence and Statistics.
Tabak, E. G., and Turner. 2013. Communications on Pure and Applied Mathematics.
Tabak, Esteban G., and Vanden-Eijnden. 2010. Communications in Mathematical Sciences.
Tokdar. 2007. Journal of Computational and Graphical Statistics.
van Lieshout. 2011. Methodology and Computing in Applied Probability.
Zeevi, and Meir. 1997. Neural Networks: The Official Journal of the International Neural Network Society.