ML Anthology

Note on Free Lunches and Cross-Validation

Cyril Goutte
NeCo 1997 pp. 1245-1249
doi:10.1162/NECO.1997.9.6.1245 /neco/1997/goutte1997neco-note/

Abstract

The “no-free-lunch” theorems (Wolpert & Macready, 1995) have sparked heated debate in the computational learning community. A recent communication (Zhu & Rohwer, 1996) attempts to demonstrate the inefficiency of cross-validation on a simple problem. We elaborate on this result by considering a broader class of cross-validation. When used more strictly, cross-validation can yield the expected results on simple examples.

NeCo Semantic Scholar

Cite

Text

Goutte. "Note on Free Lunches and Cross-Validation." Neural Computation, 1997. doi:10.1162/NECO.1997.9.6.1245

Markdown

[Goutte. "Note on Free Lunches and Cross-Validation." Neural Computation, 1997.](https://mlanthology.org/neco/1997/goutte1997neco-note/) doi:10.1162/NECO.1997.9.6.1245

BibTeX

@article{goutte1997neco-note,
  title     = {{Note on Free Lunches and Cross-Validation}},
  author    = {Goutte, Cyril},
  journal   = {Neural Computation},
  year      = {1997},
  pages     = {1245-1249},
  doi       = {10.1162/NECO.1997.9.6.1245},
  volume    = {9},
  url       = {https://mlanthology.org/neco/1997/goutte1997neco-note/}
}