A1 Refereed original research article in a scientific journal
Efficient cross-validation for kernelized least-squares regression with sparse basis expansions
Authors: Pahikkala T, Suominen H, Boberg J
Publisher: Springer Netherlands
Publication year: 2012
Journal: Machine Learning
Journal name in source: Machine Learning
Number in series: 3
Volume: 87
Issue: 3
First page : 381
Last page: 407
Number of pages: 27
ISSN: 0885-6125
DOI: https://doi.org/10.1007/s10994-012-5287-6
Web address : http://dx.doi.org/10.1007/s10994-012-5287-6
Self-archived copy’s web address: https://research.utu.fi/converis/portal/detail/Publication/3042008
We propose an efficient algorithm for calculating hold-out and cross-validation (CV) type of estimates for sparse regularized least-squares predictors. Holding out H data points with our method requires O(min(H^2n,Hn^2)) time provided that a predictor with n basis vectors is already trained. In addition to holding out training examples, also some of the basis vectors used to train the sparse regularized least-squares predictor with the whole training set can be removed from the basis vector set used in the hold-out computation. In our experiments, we demonstrate the speed improvements provided by our algorithm in practice, and we empirically show the benefits of removing some of the basis vectors during the CV rounds.
Downloadable publication This is an electronic reprint of the original article. |  |
