English

Improved Error Bounds Based on Worst Likely Assignments

Machine Learning 2015-04-02 v1 Information Theory Machine Learning math.IT Probability

Abstract

Error bounds based on worst likely assignments use permutation tests to validate classifiers. Worst likely assignments can produce effective bounds even for data sets with 100 or fewer training examples. This paper introduces a statistic for use in the permutation tests of worst likely assignments that improves error bounds, especially for accurate classifiers, which are typically the classifiers of interest.

Keywords

Cite

@article{arxiv.1504.00052,
  title  = {Improved Error Bounds Based on Worst Likely Assignments},
  author = {Eric Bax},
  journal= {arXiv preprint arXiv:1504.00052},
  year   = {2015}
}

Comments

IJCNN 2015

R2 v1 2026-06-22T09:07:29.583Z