%0 Journal Article
%T Parallel Online Learning
%A Daniel Hsu
%A Nikos Karampatziakis
%A John Langford
%A Alex Smola
%J Computer Science
%D 2011
%I arXiv
%X In this work we study parallelization of online learning, a core primitive in machine learning. In a parallel environment all known approaches for parallel online learning lead to delayed updates, where the model is updated using out-of-date information. In the worst case, or when examples are temporally correlated, delay can have a very adverse effect on the learning algorithm. Here, we analyze and present preliminary empirical results on a set of learning architectures based on a feature sharding approach that present various tradeoffs between delay, degree of parallelism, representation power and empirical performance.
%U http://arxiv.org/abs/1103.4204v1