Bayesian exponential family projections for coupled data sources

Arto Klami, Seppo Virtanen, Samuel Kaski
Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence, PMLR R8:293-300, 2010.

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 present- ing 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 ex- ponential family. The models are based on a new family of priors that are generally us- able for all such factorizations. We also in- troduce new inference strategies, and demon- strate how the methods outperform earlier ones when the Gaussianity assumption does not hold.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR8-klami10a, title = {{B}ayesian exponential family projections for coupled data sources}, author = {Klami, Arto and Virtanen, Seppo and Kaski, Samuel}, booktitle = {Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence}, pages = {293--300}, year = {2010}, editor = {Grünwald, Peter and Spirtes, Peter}, volume = {R8}, series = {Proceedings of Machine Learning Research}, month = {08--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r8/main/assets/klami10a/klami10a.pdf}, url = {https://proceedings.mlr.press/r8/klami10a.html}, 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 present- ing 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 ex- ponential family. The models are based on a new family of priors that are generally us- able for all such factorizations. We also in- troduce new inference strategies, and demon- strate how the methods outperform earlier ones when the Gaussianity assumption does not hold.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Bayesian exponential family projections for coupled data sources %A Arto Klami %A Seppo Virtanen %A Samuel Kaski %B Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2010 %E Peter Grünwald %E Peter Spirtes %F pmlr-vR8-klami10a %I PMLR %P 293--300 %U https://proceedings.mlr.press/r8/klami10a.html %V R8 %X 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 present- ing 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 ex- ponential family. The models are based on a new family of priors that are generally us- able for all such factorizations. We also in- troduce new inference strategies, and demon- strate how the methods outperform earlier ones when the Gaussianity assumption does not hold. %Z Reissued by PMLR on 04 October 2026.
APA
Klami, A., Virtanen, S. & Kaski, S.. (2010). Bayesian exponential family projections for coupled data sources. Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R8:293-300 Available from https://proceedings.mlr.press/r8/klami10a.html. Reissued by PMLR on 04 October 2026.

Related Material