Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Communication-efficient distributed online learning with kernels

: Kamp, M.; Bothe, S.; Boley, M.; Mock, M.


Frasconi, P.:
Machine learning and knowledge discovery in databases. European conference, ECML PKDD 2016. Pt.2 : Riva del Garda, Italy, September 19-23, 2016; Proceedings
Cham: Springer International Publishing, 2016 (Lecture Notes in Computer Science 9852)
ISBN: 978-3-319-46226-4 (Print)
ISBN: 978-3-319-46227-1 (Online)
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD) <15, 2016, Riva del Garda>
Conference Paper
Fraunhofer IAIS ()

We propose an efficient distributed online learning protocol for low-latency real-time services. It extends a previously presented protocol to kernelized online learners that represent their models by a support vector expansion. While such learners often achieve higher predictive performance than their linear counterparts, communicating the support vector expansions becomes inefficient for large numbers of support vectors. The proposed extension allows for a larger class of online learning algorithms-including those alleviating the problem above through model compression. In addition, we characterize the quality of the proposed protocol by introducing a novel criterion that requires the communication to be bounded by the loss suffered.