UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Learning additive models online with fast evaluating kernels

Herbster, M; (2001) Learning additive models online with fast evaluating kernels. In: (pp. pp. 444-460). Green open access

[thumbnail of wayfaster.pdf]
Preview
PDF
wayfaster.pdf
Available under License : See the attached licence file.

Download (249kB)

Abstract

We develop three new techniques to build on the recent advances in online learning with kernels. First, we show that an exponential speed-up in prediction time pertrial is possible for such algorithms as the Kernel-Adatron, the Kernel-Perceptron, and ROMMA for specific additive models. Second, we show that the techniques of the recent algorithms developed for online linear prediction when the best predictor changes over time may be implemented for kernel-based learners at no additional asymptotic cost. Finally, we introduce a new online kernel-based learning algorithm for which we give worst-case loss bounds for the ϵ-insensitive square loss.

Type: Proceedings paper
Title: Learning additive models online with fast evaluating kernels
ISBN-13: 9783540423430
Open access status: An open access version is available from UCL Discovery
DOI: 10.1007/3-540-44581-1_29
UCL classification: UCL
UCL > Provost and Vice Provost Offices
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/135665
Downloads since deposit
600Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item