Prediction with Expert Advice in Games with Unbounded One-Step Gains

Details Prediction with Expert Advice in Games with Unbounded One-Step Gains Prediction with Expert Advice in Games with Unbounded One-Step Gains

2008-06-26

arxiv.org/abs/0806.4391v1

Computer Science

Learning

16 pages

Scientific paper

The games of prediction with expert advice are considered in this paper. We present some modification of Kalai and Vempala algorithm of following the perturbed leader for the case of unrestrictedly large one-step gains. We show that in general case the cumulative gain of any probabilistic prediction algorithm can be much worse than the gain of some expert of the pool. Nevertheless, we give the lower bound for this cumulative gain in general case and construct a universal algorithm which has the optimal performance; we also prove that in case when one-step gains of experts of the pool have ``limited deviations'' the performance of our algorithm is close to the performance of the best expert.

Affiliated with

Also associated with

No associations

Rating

Prediction with Expert Advice in Games with Unbounded One-Step Gains 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 in Games with Unbounded One-Step Gains, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Prediction with Expert Advice in Games with Unbounded One-Step Gains will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-691995