Bayesian Block-Diagonal Predictive Classifier for Gaussian Data
- 1.4k Downloads
The paper presents a method for constructing Bayesian predictive classifier in a high-dimensional setting. Given that classes are represented by Gaussian distributions with block-structured covariance matrix, a closed form expression for the posterior predictive distribution of the data is established. Due to factorization of this distribution, the resulting Bayesian predictive and marginal classifier provides an efficient solution to the high-dimensional problem by splitting it into smaller tractable problems. In a simulation study we show that the suggested classifier outperforms several alternative algorithms such as linear discriminant analysis based on block-wise inverse covariance estimators and the shrunken centroids regularized discriminant analysis.
KeywordsCovariance estimators discriminant analysis high-dimensional data hyperparameters
Unable to display preview. Download preview PDF.
- 1.Bernardo, J.M., Smith, A.F.: Bayesian Theory. John Wiley & Sons, New York (1995)Google Scholar
- 5.Geisser, S.: Predictive Discrimination. In: Krishnaiah, P.R. (ed.) Multivariate Analysis. Academic Press, New York (1966)Google Scholar
- 10.Corander, J., Cui, Y., Koski, T., Sirén, J.: Predictive Gaussian Classifiers (under revision)Google Scholar
- 11.Pavlenko, T., Björkström, A., Tillander, A.: Covariance Structure Approximation via gLasso in High-Dimensional Supervissed Classification. J. Appl. Stat. (in press, 2012)Google Scholar