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
The subspace information criterion for infinite dimensional hypothesis spaces
The Journal of Machine Learning Research
Subspace Information Criterion for Model Selection
Neural Computation
In Search of Non-Gaussian Components of a High-Dimensional Distribution
The Journal of Machine Learning Research
Hi-index | 0.00 |
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.