中文

Competing with wild prediction rules

机器学习 2007-05-23 v2

摘要

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.

关键词

引用

@article{arxiv.cs/0512059,
  title  = {Competing with wild prediction rules},
  author = {Vladimir Vovk},
  journal= {arXiv preprint arXiv:cs/0512059},
  year   = {2007}
}

备注

28 pages, 3 figures