Competing with wild prediction rules

Details Competing with wild prediction rules Competing with wild prediction rules

2005-12-14

arxiv.org/abs/cs/0512059v2

Computer Science

Learning

28 pages, 3 figures

Scientific paper

We consider the problem of on-line prediction competitive with a benchmark class of continuous but highly irregular prediction rules. It is known that if the benchmark class is a reproducing kernel Hilbert space, there exists a prediction algorithm whose average loss over the first N examples does not exceed the average loss of any prediction rule in the class plus a "regret term" of O(N^(-1/2)). The elements of some natural benchmark classes, however, are so irregular that these classes are not Hilbert spaces. In this paper we develop Banach-space methods to construct a prediction algorithm with a regret term of O(N^(-1/p)), where p is in [2,infty) and p-2 reflects the degree to which the benchmark class fails to be a Hilbert space.

Affiliated with

Also associated with

No associations

Rating

Competing with wild prediction rules 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 Competing with wild prediction rules, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Competing with wild prediction rules will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-168263