CVST-package {CVST}R Documentation

Fast Cross-Validation via Sequential Testing

Description

This package implements the fast cross-validation via sequential testing (CVST) procedure. CVST is an improved cross-validation procedure which uses non-parametric testing coupled with sequential analysis to determine the best parameter set on linearly increasing subsets of the data. By eliminating underperforming candidates quickly and keeping promising candidates as long as possible, the method speeds up the computation while preserving the capability of a full cross-validation. Additionally to the CVST the package contains an implentation of the ordinary k-fold cross-validation with a flexible and powerful set of helper objects and methods to handle the overall model selection process. The implementations of the Cochran's Q test with permutations and the sequential testing framework of Wald are generic and can therefore also be used in other contexts.

Details

Package: CVST
Type: Package
Version: 0.2
Date: 2013-03-25
License: GPL (>=2.0)

Author(s)

Tammo Krueger, Mikio Braun

Maintainer: Tammo Krueger <tammokrueger@googlemail.com>

References

Tammo Krueger, Danny Panknin, and Mikio Braun. Fast cross-validation via sequential analysis. Neural Information Processing Systems (NIPS), Big Learning Workshop, 2011. URL http://biglearn.org/2011/index.php/Papers\#paper2.

Tammo Krueger, Danny Panknin, and Mikio Braun. Fast cross-validation via sequential testing. CoRR, abs/1206.2248, 2012. URL http://arxiv.org/abs/1206.2248.

Abraham Wald. Sequential Analysis. Wiley, 1947.

W. G. Cochran. The comparison of percentages in matched samples. Biometrika, 37 (3-4):256–266, 1950.

M. Friedman. The use of ranks to avoid the assumption of normality implicit in the analysis of variance. Journal of the American Statistical Association, 32 (200):675–701, 1937.

Examples

ns = noisySine(100)
svm = constructSVMLearner()
params = constructParams(kernel="rbfdot", sigma=10^(-3:3), nu=c(0.05, 0.1, 0.2, 0.3))
opt = fastCV(ns, svm, params, constructCVSTModel())

[Package CVST version 0.2-1 Index]