Generalization Error Estimation for Non-linear Learning Methods

Estimating the generalization error is one of the key ingredients of supervised learning since a good generalization error estimator can be used for model selection. An unbiased generalization error estimator called the subspace information criterion (SIC) is shown to be useful for model selection, but its range of application is limited to linear learning methods. In this paper, we extend SIC to be applicable to non-linear learning. Keywords supervised learning, generalization capability, model selection, subspace information criterion, non-linear learning

• Type: Journal
• Year: 2007
• Where: IEICET
• Authors: Masashi Sugiyama
• Keywords: Generalization Error, Generalization Error Estimator, IEICET 2007, Model Selection