Title: Optimal Cross-Validation Split Ratio: Experimental Investigation

Author: Cyril Goutte and Jan Larsen
Department of Mathematical Modeling - Building 321
Technical University of Denmark, DK-2800 Lyngby, Denmark
Phone: +45 4525 3921,3923
Fax: +45 4587 2599
E-mail: cg,jl@imm.dtu.dk


Cross-validation is a common method for assessing the generalisation ability of a model in order to tune a regularisation parameter or other hyper-parameters of a learning process. The use of cross-validation requires to set yet an additional parameter, the split rati. While a few texts have investigated theoretically the asymptotic setting of this ratio, no consensus has emerged. In this contribution, we investigate the sensitivity and optimal setting of the split ratio on a particular model, a non-parametric kernel estimator with adaptive metric.

Preprint, appears in L. Niklasson, M. Bodén and T. Ziemke (eds), Proceedings of the 8th International Conference on Artificial Neural Networks (ICANN'98, Skovde), Perspectives in Neural Computing, Berlin:Springer Verlag, vol. 2, pp. 681-686.

Download: abstract, Compressed Postscript.