Open Access
2010 Noisy independent factor analysis model for density estimation and classification
Umberto Amato, Anestis Antoniadis, Alexander Samarov, Alexandre B. Tsybakov
Electron. J. Statist. 4: 707-736 (2010). DOI: 10.1214/09-EJS498


We consider the problem of multivariate density estimation when the unknown density is assumed to follow a particular form of dimensionality reduction, a noisy independent factor analysis (IFA) model. In this model the data are generated by a number of latent independent components having unknown distributions and are observed in Gaussian noise. We do not assume that either the number of components or the matrix mixing the components are known. We show that the densities of this form can be estimated with a fast rate. Using the mirror averaging aggregation algorithm, we construct a density estimator which achieves a nearly parametric rate $(\log^{1/4}{n})/\sqrt{n}$, independent of the dimensionality of the data, as the sample size n tends to infinity. This estimator is adaptive to the number of components, their distributions and the mixing matrix. We then apply this density estimator to construct nonparametric plug-in classifiers and show that they achieve the best obtainable rate of the excess Bayes risk, to within a logarithmic factor independent of the dimension of the data. Applications of this classifier to simulated data sets and to real data from a remote sensing experiment show promising results.


Download Citation

Umberto Amato. Anestis Antoniadis. Alexander Samarov. Alexandre B. Tsybakov. "Noisy independent factor analysis model for density estimation and classification." Electron. J. Statist. 4 707 - 736, 2010.


Published: 2010
First available in Project Euclid: 12 August 2010

zbMATH: 1329.62273
MathSciNet: MR2678968
Digital Object Identifier: 10.1214/09-EJS498

Primary: 62H25
Secondary: 62G07 , 62H30

Keywords: Aggregation , independent factor analysis , Nonparametric density estimation , plug-in classifier , remote sensing

Rights: Copyright © 2010 The Institute of Mathematical Statistics and the Bernoulli Society

Back to Top