A survey of cross-validation procedures for model selection

Abstract : Used to estimate the risk of an estimator or to perform model selection, cross-validation is a widespread strategy because of its simplicity and its apparent universality. Many results exist on the model selection performances of cross-validation procedures. This survey intends to relate these results to the most recent advances of model selection theory, with a particular emphasis on distinguishing empirical statements from rigorous theoretical results. As a conclusion, guidelines are provided for choosing the best cross-validation procedure according to the particular features of the problem in hand.
Complete list of metadatas

Cited literature [130 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00407906
Contributor : Alain Celisse <>
Submitted on : Monday, July 27, 2009 - 7:24:11 PM
Last modification on : Tuesday, July 3, 2018 - 11:29:30 AM
Long-term archiving on : Tuesday, June 15, 2010 - 9:27:56 PM

Files

preprintLilleArlotCelisse.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Sylvain Arlot, Alain Celisse. A survey of cross-validation procedures for model selection. Statistics Surveys, Institute of Mathematical Statistics (IMS), 2010, 4, pp.40--79. ⟨10.1214/09-SS054⟩. ⟨hal-00407906⟩

Share

Metrics

Record views

4961

Files downloads

1759