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.
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