Variational Bayesian Inference For A Scale Mixture Of Normal Distributions Handling Missing Data
This addresses data robustness issues in statistical modeling for domains with incomplete or noisy data, but it is incremental as it builds on existing mixture model and variational methods.
The paper tackles classification and clustering of data with outliers and missing values by developing a scale mixture of Normal distributions model, using Variational Bayesian Inference for learning, supervised classification, and clustering.
In this paper, a scale mixture of Normal distributions model is developed for classification and clustering of data having outliers and missing values. The classification method, based on a mixture model, focuses on the introduction of latent variables that gives us the possibility to handle sensitivity of model to outliers and to allow a less restrictive modelling of missing data. Inference is processed through a Variational Bayesian Approximation and a Bayesian treatment is adopted for model learning, supervised classification and clustering.