| |
|
| |
|
Nathan Srebro
University of Toronto
Maximum Margin Matrix Factorization
March 17, 2006 10:00am
Abstract:
Factor, or linear component (PCA), models are often natural in the analysis of many kinds of tabulated data (e.g. collections of documents or images, gene expression measurements and user preferences). The premise of such models is that important aspects of the data can be captured by a small number dimensions ("components", "factors" or "topics").
I will present a novel approach that allows an unbounded (infinite) number of factors. This is achieved by limiting the norm of the factorization instead of its dimensionality. The approach is inspired by, and has strong connections to, large-margin linear discrimination.
I will show how such a max-margin matrix factorization can be learned by solving a (very large, but efficiently solvable) semi-definite program. I will also present generalization error bounds for learning with such factorization, and discuss the relationship between what can be learned with max-margin and low-dimensional factorizations.
Joint work with Alexandre d'Aspremont, Tommi Jaakkola and Jason Rennie and Adi Shraibman.
If you have questions, or would like to meet the speaker, please contact Ponda at 4-1994 or pondabarnes@tti-c.org. For information on future TTI-C talks or events, please go to the TTI-C Events page.