A consistent framework for structure machine learning

Lorenzo Rosasco
Università di Genova

We propose and analyze a regularization approach for structured prediction problems. We characterize a large class of loss functions that allows to naturally embed structured outputs in a linear space. We exploit this fact to design learning algorithms using a surrogate approach and regularization techniques. We prove universal consistency and finite sample bounds characterizing the generalization properties of the proposed methods. Experimental results demonstrate the practical usefulness of the proposed approach.

Presentation (PDF File)

Back to Workshop III: Geometry of Big Data