Bayesian exponential family projections for coupled data sources

File Description SizeFormat 
1203.3489v1.pdfPublished version421.98 kBAdobe PDFView/Open
Title: Bayesian exponential family projections for coupled data sources
Authors: Klami, A
Virtanen, S
Kaski, S
Item Type: Journal Article
Abstract: Exponential family extensions of principal component analysis (EPCA) have received a considerable amount of attention in recent years, demonstrating the growing need for basic modeling tools that do not assume the squared loss or Gaussian distribution. We extend the EPCA model toolbox by presenting the first exponential family multi-view learning methods of the partial least squares and canonical correlation analysis, based on a unified representation of EPCA as matrix factorization of the natural parameters of exponential family. The models are based on a new family of priors that are generally usable for all such factorizations. We also introduce new inference strategies, and demonstrate how the methods outperform earlier ones when the Gaussianity assumption does not hold.
URI: http://hdl.handle.net/10044/1/52932
Copyright Statement: © The Authors
Keywords: cs.LG
stat.ML
Notes: Appears in Proceedings of the Twenty-Sixth Conference on Uncertainty in Artificial Intelligence (UAI2010)
Appears in Collections:Mathematics
Statistics
Faculty of Natural Sciences



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commonsx