Master Algorithms for Active Experts Problems based on Increasing Loss Values

Details Master Algorithms for Active Experts Problems based on Increasing Loss Values Master Algorithms for Active Experts Problems based on Increasing Loss Values

2005-02-15

arxiv.org/abs/cs/0502067v1

Proc. 14th Dutch-Belgium Conf. on Machine Learning (Benelearn 2005) 59-66

Computer Science

Learning

8 two-column pages, latex2e

Scientific paper

We specify an experts algorithm with the following characteristics: (a) it uses only feedback from the actions actually chosen (bandit setup), (b) it can be applied with countably infinite expert classes, and (c) it copes with losses that may grow in time appropriately slowly. We prove loss bounds against an adaptive adversary. From this, we obtain master algorithms for "active experts problems", which means that the master's actions may influence the behavior of the adversary. Our algorithm can significantly outperform standard experts algorithms on such problems. Finally, we combine it with a universal expert class. This results in a (computationally infeasible) universal master algorithm which performs - in a certain sense - almost as well as any computable strategy, for any online problem.

Affiliated with

Also associated with

No associations

Rating

Master Algorithms for Active Experts Problems based on Increasing Loss Values 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 Master Algorithms for Active Experts Problems based on Increasing Loss Values, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Master Algorithms for Active Experts Problems based on Increasing Loss Values will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-242528