Combining Train Set and Test Set Bounds (0)
| Venue: | In: Proc. 19th International Conference on Machine Learning |
| Citations: | 5 - 2 self |
BibTeX
@INPROCEEDINGS{Langford_combiningtrain,
author = {John Langford},
title = {Combining Train Set and Test Set Bounds},
booktitle = {In: Proc. 19th International Conference on Machine Learning},
year = {},
pages = {331--338},
publisher = {Morgan Kaufmann}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
This paper is about bounds on future error rates. We present a theorem for combining an arbitrary test set based bound with an arbitrary training set based bound. Appropriate use of this theorem results in a combined bound with two properties: 1) the combined bound is never much worse than either the training set based bound or the test set based bound and 2) the combined bound is sometimes better than either bound individually. Empirical validation is presented showing the effectiveness of the combined bound.
