Slow Learners are Fast

Details Slow Learners are Fast Slow Learners are Fast

2009-11-03

arxiv.org/abs/0911.0491v1

Mathematics

Optimization and Control

Extended version of conference paper - NIPS 2009

Scientific paper

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.

Affiliated with

Also associated with

No associations

Rating

Slow Learners are Fast does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Slow Learners are Fast, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Slow Learners are Fast will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-256212