[ACM Press the 23rd international conference - Pittsburgh, Pennsylvania (2006.06.25-2006.06.29)] Proceedings of the 23rd international conference on Machine learning - ICML '06 - Robust probabilistic projections

✍ Scribed by Archambeau, Cédric; Delannay, Nicolas; Verleysen, Michel

• Book ID: 121774509
• Publisher: ACM Press
• Year: 2006
• Weight: 264 KB
• Category: Article
• ISBN-13: 9781595933836
• DOI: 10.1145/1143844.1143849

✦ Synopsis

Principal components and canonical correlations are at the root of many exploratory data mining techniques and provide standard pre-processing tools in machine learning. Lately, probabilistic reformulations of these methods have been proposed . They are based on a Gaussian density model and are therefore, like their non-probabilistic counterpart, very sensitive to atypical observations. In this paper, we introduce robust probabilistic principal component analysis and robust probabilistic canonical correlation analysis. Both are based on a Student-t density model. The resulting probabilistic reformulations are more suitable in practice as they handle outliers in a natural way. We compute maximum likelihood estimates of the parameters by means of the EM algorithm.