We propose practical recommendations for selecting metaparameters for SVM regression (that is, ε -insensitive zone and regularization parameter C). The proposed methodology advocates analytic parameter selection directly from the training data, rather than resampling approaches commonly used in SVM applications. Good generalization performance of the proposed parameter selection is demonstrated...

Feature selection is a fundamental process in many classifier design problems. However, it is NP-complete and approximate approaches often require requires extensive exploration and evaluation. This paper describes a novel approach that represents feature selection as a continuous regularization problem which has a single, global minimum, where the model s complexity is measured using a 1-norm ...

Prior knowledge can be introduced into system identiication problems in terms of constraints on the parameter space, or regularizing penalty functions in a prediction error criterion. The contribution of this work is mainly an extention of the well known FPE (Final Prediction Error) statistic to the case when the system identiication problem is constrainted and contains a regularization penalty...

Recently, L1 regularization have been attracted extensive attention and successfully applied in mean-variance portfolio selection for promoting out-of-sample properties and decreasing transaction costs. However, L1 regularization approach is ineffective in promoting sparsity and selecting regularization parameter on index tracking with the budget and no-short selling constraints, since the 1-no...

The problem of learning a sparse conic combination of kernel functions or kernel matrices for classification or regression can be achieved via the regularization by a block 1-norm [1]. In this paper, we present an algorithm that computes the entire regularization path for these problems. The path is obtained by using numerical continuation techniques, and involves a running time complexity that...