Communication-Efficient Distributed Online Learning with Kernels

Kamp, Michael and Bothe, Sebastian and Boley, Mario and Mock, Michael: Communication-Efficient Distributed Online Learning with Kernels. Machine Learning and Knowledge Discovery in Databases, Springer International Publishing, 2016.

Abstract

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.

BibTeX (Download)

@conference{kamp2016communication,
title = {Communication-Efficient Distributed Online Learning with Kernels},
author = {Kamp, Michael
and Bothe, Sebastian
and Boley, Mario
and Mock, Michael},
editor = {Frasconi, Paolo
and Landwehr, Niels
and Manco, Giuseppe
and Vreeken, Jilles},
url = {http://michaelkamp.org/wp-content/uploads/2020/03/Paper467.pdf},
year  = {2016},
date = {2016-09-16},
booktitle = {Machine Learning and Knowledge Discovery in Databases},
pages = {805--819},
publisher = {Springer International Publishing},
abstract = {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.},
keywords = {communication-efficient, distributed, dynamic averaging, federated learning, kernel methods, parallelization},
pubstate = {published},
tppubtype = {conference}
}