Data-Distributed Weighted Majority and Online Mirror Descent

Details Data-Distributed Weighted Majority and Online Mirror Descent Data-Distributed Weighted Majority and Online Mirror Descent

2011-05-11

arxiv.org/abs/1105.2274v1

Computer Science

Learning

Scientific paper

In this paper, we focus on the question of the extent to which online learning can benefit from distributed computing. We focus on the setting in which $N$ agents online-learn cooperatively, where each agent only has access to its own data. We propose a generic data-distributed online learning meta-algorithm. We then introduce the Distributed Weighted Majority and Distributed Online Mirror Descent algorithms, as special cases. We show, using both theoretical analysis and experiments, that compared to a single agent: given the same computation time, these distributed algorithms achieve smaller generalization errors; and given the same generalization errors, they can be $N$ times faster.

Affiliated with

Also associated with

No associations

Rating

Data-Distributed Weighted Majority and Online Mirror Descent 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 Data-Distributed Weighted Majority and Online Mirror Descent, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Data-Distributed Weighted Majority and Online Mirror Descent will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-612186