# Density estimation

## Especially non- or semiparametrically

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?

## 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.

## 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?

## Connection to point processes

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

🏗

## Mixture models

See mixture models.

## Gaussian processes

Gaussian process can provide posterioer densities over densities somehow?

## Renormalizing flow models

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

## 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.

## Kernel density estimators

a.k.a. kernel smoothing.

### 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.

## References

Andrews, Donald W. K. 1991. Journal of Econometrics 47 (2): 359–77.
Arnold, Barry C., Enrique Castillo, and Jose M. Sarabia. 1999. Conditional Specification of Statistical Models. Springer Science & Business Media.
Barron, Andrew R., and Chyong-Hwa Sheu. 1991. The Annals of Statistics 19 (3): 1347–69.
Bashtannyk, David M., and Rob J. Hyndman. 2001. Computational Statistics & Data Analysis 36 (3): 279–98.
Battey, Heather, and Han Liu. 2013. arXiv:1308.3968 [Stat], August.
Berman, Mark, and Peter Diggle. 1989. Journal of the Royal Statistical Society. Series B (Methodological) 51 (1): 81–92.
Birgé, Lucien. 2008. arXiv:0808.1416 [Math, Stat], August.
Bosq, Denis. 1998. Nonparametric Statistics for Stochastic Processes: Estimation and Prediction. 2nd ed. Lecture Notes in Statistics 110. New York: Springer.
Cox, D. R. 1965. Journal of the Royal Statistical Society: Series B (Methodological) 27 (2): 332–37.
Cunningham, John P., Krishna V. Shenoy, and Maneesh Sahani. 2008. In Proceedings of the 25th International Conference on Machine Learning, 192–99. ICML ’08. New York, NY, USA: ACM Press.
Devroye, Luc, and Gábor Lugosi. 2001. Combinatorial Methods in Density Estimation. Springer Series in Statistics. New York: Springer.
Dinh, Vu, Lam Si Tung Ho, Duy Nguyen, and Binh T. Nguyen. 2016. In NIPS.
Efromovich, Sam. 2007. The Annals of Statistics 35 (6): 2504–35.
Eilers, Paul H. C., and Brian D. Marx. 1996. Statistical Science 11 (2): 89–121.
Ellis, Steven P. 1991. Stochastic Processes and Their Applications 39 (2): 345–58.
Giesecke, K., H. Kakavand, and M. Mousavi. 2008. In Simulation Conference, 2008. WSC 2008. Winter, 560–68.
Gu, Chong. 1993. Journal of the American Statistical Association 88 (422): 495–504.
Hall, Peter. 1987. The Annals of Statistics 15 (4): 1491–1519.
Hall, Peter, Jeff Racine, and Qi Li. 2004. Journal of the American Statistical Association 99 (468): 1015–26.
Hansen, Bruce E. 2004. Unpublished Manuscript.
Hasminskii, Rafael, and Ildar Ibragimov. 1990. The Annals of Statistics 18 (3): 999–1010.
Ibragimov, I. 2001. In Institute of Mathematical Statistics Lecture Notes - Monograph Series, 359–83. Beachwood, OH: Institute of Mathematical Statistics.
Koenker, Roger, and Ivan Mizera. 2006. Advances in Statistical Modeling and Inference, 613–34.
Kooperberg, Charles, and Charles J. Stone. 1991. Computational Statistics & Data Analysis 12 (3): 327–47.
———. 1992. Journal of Computational and Graphical Statistics 1 (4): 301–28.
Lee, Holden, Rong Ge, Tengyu Ma, Andrej Risteski, and Sanjeev Arora. 2017. In arXiv:1702.07028 [Cs].
Lenk, Peter J. 2003. Journal of Computational and Graphical Statistics 12 (3): 548–65.
Li, Ker-Chau. 1987. The Annals of Statistics 15 (3): 958–75.
Lieshout, Marie-Colette N. M. van. 2011. Methodology and Computing in Applied Probability 14 (3): 567–78.
Norets, Andriy. 2010. The Annals of Statistics 38 (3): 1733–66.
Panaretos, Victor M., and Yoav Zemel. 2016. The Annals of Statistics 44 (2): 771–812.
Papangelou, F. 1974. Zeitschrift Für Wahrscheinlichkeitstheorie Und Verwandte Gebiete 28 (3): 207–26.
Reynaud-Bouret, Patricia, Vincent Rivoirard, and Christine Tuleau-Malot. 2011. Journal of Statistical Planning and Inference 141 (1): 115–39.
Sardy, Sylvain, and Paul Tseng. 2010. Scandinavian Journal of Statistics 37 (2): 321–37.
Schoenberg, Frederic Paik. 2005. Journal of Statistical Planning and Inference 128 (1): 79–93.
Schuster, Ingmar, Mattes Mollenhauer, Stefan Klus, and Krikamol Muandet. 2019. arXiv:1905.11255 [Cs, Math, Stat], May.
Shimazaki, Hideaki, and Shigeru Shinomoto. 2010. Journal of Computational Neuroscience 29 (1-2): 171–82.
Sriperumbudur, Bharath, Kenji Fukumizu, Arthur Gretton, Aapo Hyvärinen, and Revant Kumar. 2017. Journal of Machine Learning Research 18 (57).
Sugiyama, Masashi, Ichiro Takeuchi, Taiji Suzuki, Takafumi Kanamori, Hirotaka Hachiya, and Daisuke Okanohara. 2010. In International Conference on Artificial Intelligence and Statistics, 781–88.
Tabak, E. G., and Cristina V. Turner. 2013. Communications on Pure and Applied Mathematics 66 (2): 145–64.
Tabak, Esteban G., and Eric Vanden-Eijnden. 2010. Communications in Mathematical Sciences 8 (1): 217–33.
Tokdar, Surya T. 2007. Journal of Computational and Graphical Statistics 16 (3): 633–55.
Zeevi, Assaf J., and Ronny Meir. 1997. Neural Networks: The Official Journal of the International Neural Network Society 10 (1): 99–109.

### No comments yet. Why not leave one?

GitHub-flavored Markdown & a sane subset of HTML is supported.