Multivariate Density Estimation with Deep Neural Mixture Models

TL;DR

This paper introduces Deep Neural Mixture Models (DNMMs) for multivariate density estimation, providing a novel approach that combines neural networks with mixture models, ensuring probabilistic validity and demonstrating superior performance over traditional methods.

Contribution

The paper extends Neural Mixture Densities to multivariate DNN mixtures, proposing a maximum-likelihood training algorithm and an automatic architecture selection procedure.

Findings

DNMMs effectively model complex multivariate densities.

Experimental results show DNMMs outperform traditional density estimation methods.

The approach satisfies Kolmogorov's axioms numerically.

Abstract

Albeit worryingly underrated in the recent literature on machine learning in general (and, on deep learning in particular), multivariate density estimation is a fundamental task in many applications, at least implicitly, and still an open issue. With a few exceptions, deep neural networks (DNNs) have seldom been applied to density estimation, mostly due to the unsupervised nature of the estimation task, and (especially) due to the need for constrained training algorithms that ended up realizing proper probabilistic models that satisfy Kolmogorov's axioms. Moreover, in spite of the well-known improvement in terms of modeling capabilities yielded by mixture models over plain single-density statistical estimators, no proper mixtures of multivariate DNN-based component densities have been investigated so far. The paper fills this gap by extending our previous work on Neural Mixture Densities (NMMs) to multivariate DNN mixtures. A maximum-likelihood (ML) algorithm for estimating Deep NMMs (DNMMs) is handed out, which satisfies numerically a combination of hard and soft constraints aimed at ensuring satisfaction of Kolmogorov's axioms. The class of probability density functions that can be modeled to any degree of precision via DNMMs is formally defined. A procedure for the automatic selection of the DNMM architecture, as well as of the hyperparameters for its ML training algorithm, is presented (exploiting the probabilistic nature of the DNMM). Experimental results on univariate and multivariate data are reported on, corroborating the effectiveness of the approach and its superiority to the most popular statistical estimation techniques.