Probabilistic Classification by Density Estimation Using Gaussian Mixture Model and Masked Autoregressive Flow
This work proposes a probabilistic classification approach for machine learning applications, but it is incremental as it adapts existing density estimation methods to classification.
The paper tackles classification by modeling class likelihoods using Gaussian Mixture Models and Masked Autoregressive Flow for density estimation, resulting in improved performance over simpler Gaussian-based classifiers like linear discriminant analysis.
Density estimation, which estimates the distribution of data, is an important category of probabilistic machine learning. A family of density estimators is mixture models, such as Gaussian Mixture Model (GMM) by expectation maximization. Another family of density estimators is the generative models which generate data from input latent variables. One of the generative models is the Masked Autoregressive Flow (MAF) which makes use of normalizing flows and autoregressive networks. In this paper, we use the density estimators for classification, although they are often used for estimating the distribution of data. We model the likelihood of classes of data by density estimation, specifically using GMM and MAF. The proposed classifiers outperform simpler classifiers such as linear discriminant analysis which model the likelihood using only a single Gaussian distribution. This work opens the research door for proposing other probabilistic classifiers based on joint density estimation.