Online Learning in Case of Unbounded Losses Using the Follow Perturbed Leader Algorithm

Details Online Learning in Case of Unbounded Losses Using the Follow Perturbed Leader Algorithm Online Learning in Case of Unbounded Losses Using the Follow Perturbed Leader Algorithm

2010-08-25

arxiv.org/abs/1008.4232v1

Computer Science

Learning

31 pages, 3 figures

Scientific paper

In this paper the sequential prediction problem with expert advice is considered for the case where losses of experts suffered at each step cannot be bounded in advance. We present some modification of Kalai and Vempala algorithm of following the perturbed leader where weights depend on past losses of the experts. New notions of a volume and a scaled fluctuation of a game are introduced. We present a probabilistic algorithm protected from unrestrictedly large one-step losses. This algorithm has the optimal performance in the case when the scaled fluctuations of one-step losses of experts of the pool tend to zero.

Affiliated with

Also associated with

No associations

Rating

Online Learning in Case of Unbounded Losses Using the Follow Perturbed Leader Algorithm 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 Online Learning in Case of Unbounded Losses Using the Follow Perturbed Leader Algorithm, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Online Learning in Case of Unbounded Losses Using the Follow Perturbed Leader Algorithm will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-525140