Multi-task and lifelong learning of kernels Conference Paper

Author(s): Pentina, Anastasia; Ben-David, Shai
Title: Multi-task and lifelong learning of kernels
Title Series: LNCS
Affiliation IST Austria
Abstract: We consider a problem of learning kernels for use in SVM classification in the multi-task and lifelong scenarios and provide generalization bounds on the error of a large margin classifier. Our results show that, under mild conditions on the family of kernels used for learning, solving several related tasks simultaneously is beneficial over single task learning. In particular, as the number of observed tasks grows, assuming that in the considered family of kernels there exists one that yields low approximation error on all tasks, the overhead associated with learning such a kernel vanishes and the complexity converges to that of learning when this good kernel is given to the learner.
Keywords: Kernel learning; Lifelong learning; Multi-task learning
Conference Title: ALT: Algorithmic Learning Theory
Volume: 9355
Conference Dates: October 4 - 6, 2015
Conference Location: Banff, Canada
Publisher: Springer  
Date Published: 2015-01-01
Start Page: 194
End Page: 208
Sponsor: This work was in parts funded by the European Research Council under the European Union’s Seventh Framework Programme (FP7/2007- 2013)/ERC grant agreement no 308036.
DOI: 10.1007/978-3-319-24486-0_13
Open access: yes (repository)
IST Austria Authors
Related IST Austria Work