Generalization Error Estimation for Non-linear Learning Methods

Authors:
Masashi Sugiyama
Affiliations:
-
Venue:
IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
Year:
2007

Citing 8
Cited 0

Regularization theory and neural networks architectures

Neural Computation
Bayesian regularization and pruning using a Laplace prior

Neural Computation
Atomic Decomposition by Basis Pursuit

SIAM Journal on Scientific Computing
Theoretical and Experimental Evaluation of the Subspace Information Criterion

Machine Learning
The subspace information criterion for infinite dimensional hypothesis spaces

The Journal of Machine Learning Research
Subspace Information Criterion for Model Selection

Neural Computation
Additive Regularization Trade-Off: Fusion of Training and Validation Levels in Kernel Methods

Machine Learning
In Search of Non-Gaussian Components of a High-Dimensional Distribution

The Journal of Machine Learning Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.