Sciweavers

Share
CORR
2011
Springer

Parallel Online Learning

8 years 8 days ago
Parallel Online Learning
Online learning algorithms have impressive convergence properties when it comes to risk minimization and convex games on very large problems. However, they are inherently sequential in their design which prevents them from taking advantage of modern multi-core architectures. In this paper we prove that online learning with delayed updates converges well, thereby facilitating parallel online learning.
Daniel Hsu, Nikos Karampatziakis, John Langford, A
Added 13 May 2011
Updated 13 May 2011
Type Journal
Year 2011
Where CORR
Authors Daniel Hsu, Nikos Karampatziakis, John Langford, Alexander J. Smola
Comments (0)
books