Learning kernels using local Rademacher complexity Conference Paper
| Authors: | Cortes, C.; Kloft, M.; Mohri, M. |
| Title: | Learning kernels using local Rademacher complexity |
| Conference Title: | 26th Annual Conference on Neural Information Processing Systems, NIPS 2013 |
| Abstract: | We use the notion of local Rademacher complexity to design new algorithms for learning kernels. Our algorithms thereby benefit from the sharper learning bounds based on that notion which, under certain general conditions, guarantee a faster convergence rate. We devise two new learning kernel algorithms: one based on a convex optimization problem for which we give an efficient solution using existing learning kernel techniques, and another one that can be formulated as a DC-programming problem for which we describe a solution in detail. We also report the results of experiments with both algorithms in both binary and multi-class classification tasks. |
| Keywords: | convex optimization; convex optimization problems; faster convergence; learning kernels; multi-class classification; rademacher complexity; learning algorithms |
| Journal Title | Advances in Neural Information Processing Systems |
| Conference Dates: | 2013 Dec 5-10 |
| Conference Location: | Lake Tahoe, NV |
| ISBN: | 1049-5258 |
| Publisher: | Neural Information Processing Systems Foundation |
| Location: | Lake Tahoe, NV |
| Date Published: | 2013-01-01 |
| Language: | English |
| PROVIDER: | scopus |
| DOI/URL: | |
| Notes: | Adv. neural inf. proces. syst. -- Conference code: 104690 -- Export Date: 2 June 2014 -- 5 December 2013 through 10 December 2013 -- Source: Scopus |
MSK Authors
-
6Kloft
Related MSK Work