This paper proposes a canonical-correlation-based filter method for feature selection. The sum of squared canonical correlation coefficients is adopted as the feature ranking criterion. The proposed method boosts the computational speed of the ranking criterion in greedy search. The supporting theorems developed for the feature selection method are fundamental to the understanding of the canonical correlation analysis. In empirical studies, a synthetic dataset is used to demonstrate the speed advantage of the proposed method, and eight real datasets are applied to show the effectiveness of the proposed feature ranking criterion in both classification and regression. The results show that the proposed method is considerably faster than the definition-based method, and the proposed ranking criterion is competitive compared with the seven mutual-information-based criteria.

An Orthogonal Least Squares (OLS) based feature selection method is proposed for both binomial and multinomial classification. The novel Squared Orthogonal Correlation Coefficient (SOCC) is defined based on Error Reduction Ratio (ERR) in OLS and used as the feature ranking criterion. The equivalence between the canonical correlation coefficient, Fisher's criterion, and the sum of the SOCCs is revealed, which unveils the statistical implication of ERR in OLS for the first time. It is also shown that the OLS based feature selection method has speed advantages when applied for greedy search. The proposed method is comprehensively compared with the mutual information based feature selection methods in 2 synthetic and 7 real world datasets. The results show that the proposed method is always in the top 5 among the 10 candidate methods. Besides, the proposed method can be directly applied to continuous features without discretisation, which is another significant advantage over mutual information based methods.

Canonical correlation analysis (CCA) is a fundamental statistical tool for exploring the correlation structure between two sets of random variables. In this paper, motivated by recent success of applying CCA to learn low dimensional representations of high dimensional objects, we propose to quantify the estimation loss of CCA by the excess prediction loss defined through a prediction-after-dimension-reduction framework. Such framework suggests viewing CCA estimation as estimating the subspaces spanned by the canonical variates. Interestedly, the proposed error metrics derived from the excess prediction loss turn out to be closely related to the principal angles between the subspaces spanned by the population and sample canonical variates respectively. We characterize the non-asymptotic minimax rates under the proposed metrics, especially the dependency of the minimax rates on the key quantities including the dimensions, the condition number of the covariance matrices, the canonical correlations and the eigen-gap, with minimal assumptions on the joint covariance matrix. To the best of our knowledge, this is the first finite sample result that captures the effect of the canonical correlations on the minimax rates.