Cross-Validation Estimates IMSE
Abstract
Integrated Mean Squared Error (IMSE) is a version of the usual mean squared error criterion, averaged over all possible training If it could be observed, it could be used sets of a given size. to determine optimal network complexity or optimal data sub(cid:173) sets for efficient training. We show that two common methods of cross-validating average squared error deliver unbiased estimates of IMSE, converging to IMSE with probability one. These esti(cid:173) mates thus make possible approximate IMSE-based choice of net(cid:173) work complexity. We also show that two variants of cross validation measure provide unbiased IMSE-based estimates potentially useful for selecting optimal data subsets.
Cite
Text
Plutowski et al. "Cross-Validation Estimates IMSE." Neural Information Processing Systems, 1993.Markdown
[Plutowski et al. "Cross-Validation Estimates IMSE." Neural Information Processing Systems, 1993.](https://mlanthology.org/neurips/1993/plutowski1993neurips-crossvalidation/)BibTeX
@inproceedings{plutowski1993neurips-crossvalidation,
title = {{Cross-Validation Estimates IMSE}},
author = {Plutowski, Mark and Sakata, Shinichi and White, Halbert},
booktitle = {Neural Information Processing Systems},
year = {1993},
pages = {391-398},
url = {https://mlanthology.org/neurips/1993/plutowski1993neurips-crossvalidation/}
}