dc.contributor.advisor | Tomaso Poggio | |
dc.contributor.author | Mroueh, Youssef | en_US |
dc.contributor.author | Poggio, Tomaso | en_US |
dc.contributor.author | Rosasco, Lorenzo | en_US |
dc.contributor.author | Slotine, Jean-Jacques E. | en_US |
dc.contributor.other | Center for Biological and Computational Learning (CBCL) | en_US |
dc.date.accessioned | 2011-09-27T20:30:07Z | |
dc.date.available | 2011-09-27T20:30:07Z | |
dc.date.issued | 2011-09-27 | |
dc.identifier.uri | http://hdl.handle.net/1721.1/66085 | |
dc.description.abstract | We study multi-category classification in the framework of computational learning theory. We show how a relaxation approach, which is commonly used in binary classification, can be generalized to the multi-class setting. We propose a vector coding, namely the simplex coding, that allows to introduce a new notion of multi-class margin and cast multi-category classification into a vector valued regression problem. The analysis of the relaxation error be quantified and the binary case is recovered as a special case of our theory. From a computational point of view we can show that using the simplex coding we can design regularized learning algorithms for multi-category classification that can be trained at a complexity which is independent to the number of classes. | en_US |
dc.format.extent | 3 p. | en_US |
dc.relation.ispartofseries | MIT-CSAIL-TR-2011-043 | |
dc.relation.ispartofseries | CBCL-305 | |
dc.subject | computational learning | en_US |
dc.subject | machine learning | en_US |
dc.subject | convex relaxation | en_US |
dc.title | Multi-Class Learning: Simplex Coding And Relaxation Error | en_US |
dc.language.rfc3066 | en-US | |