A New Meta-Criterion for Regularized Subspace Information Criterion

Yasushi HIDAKA  Masashi SUGIYAMA  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E90-D   No.11   pp.1779-1786
Publication Date: 2007/11/01
Online ISSN: 1745-1361
DOI: 10.1093/ietisy/e90-d.11.1779
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Pattern Recognition
Keyword: 
supervised learning,  generalization capability,  model selection,  unbiased estimator,  regularized subspace information criterion,  

Full Text: PDF>>
Buy this Article




Summary: 
In order to obtain better generalization performance in supervised learning, model parameters should be determined appropriately, i.e., they should be determined so that the generalization error is minimized. However, since the generalization error is inaccessible in practice, the model parameters are usually determined so that an estimator of the generalization error is minimized. The regularized subspace information criterion (RSIC) is such a generalization error estimator for model selection. RSIC includes an additional regularization parameter and it should be determined appropriately for better model selection. A meta-criterion for determining the regularization parameter has also been proposed and shown to be useful in practice. In this paper, we show that there are several drawbacks in the existing meta-criterion and give an alternative meta-criterion that can solve the problems. Through simulations, we show that the use of the new meta-criterion further improves the model selection performance.