Part of Advances in Neural Information Processing Systems 22 (NIPS 2009)
Martin Zinkevich, John Langford, Alex Smola
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.