Prediction with Expert Advice by Following the Perturbed Leader for General Weights

Details Prediction with Expert Advice by Following the Perturbed Leader for General Weights Prediction with Expert Advice by Following the Perturbed Leader for General Weights

2004-05-12

arxiv.org/abs/cs/0405043v2

Proc. 15th International Conf. on Algorithmic Learning Theory (ALT-2004), pages 279-293

Computer Science

Learning

16 LaTeX pages

Scientific paper

When applying aggregating strategies to Prediction with Expert Advice, the learning rate must be adaptively tuned. The natural choice of sqrt(complexity/current loss) renders the analysis of Weighted Majority derivatives quite complicated. In particular, for arbitrary weights there have been no results proven so far. The analysis of the alternative "Follow the Perturbed Leader" (FPL) algorithm from Kalai (2003} (based on Hannan's algorithm) is easier. We derive loss bounds for adaptive learning rate and both finite expert classes with uniform weights and countable expert classes with arbitrary weights. For the former setup, our loss bounds match the best known results so far, while for the latter our results are (to our knowledge) new.

Affiliated with

Also associated with

No associations

Rating

Prediction with Expert Advice by Following the Perturbed Leader for General Weights 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 Prediction with Expert Advice by Following the Perturbed Leader for General Weights, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Prediction with Expert Advice by Following the Perturbed Leader for General Weights will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-536456