A Bayesian Framework for Learning Shared and Individual Subspaces from Multiple Data Sources

space learning for multi-view data: a large margin approach .WIDE: A real-world web image database from national university of singapore. sampling for Bayesian non-conjugate and hierarchical models by using auxiliary variables. A choice model with infinitely many latent features. [6] T. Griffiths and Z. Ghahramani. Infinite latent feature models and the Indian buffet process. nonparametric joint factor model for learning shared and individual subspaces from multiple data sources.plementary material for UAI-12 publication " A slice sampler for restricted hierarchical beta process with applications to shared subspace learn-ing". [10] N.L. Hjort. Nonparametric Bayes estimators based on beta processes in models for life history data. [14] D. Knowles and Z. Ghahramani. Infinite sparse factor analysis and infinite independent components analysis .ciated text and images with dual-wing harmoniums. Harmonium models for semantic video representation and classification.