Boosting Ridge Regression for High Dimensional Data Classification
This work addresses computational efficiency for high-dimensional data classification, offering an incremental improvement over standard ridge regression methods.
The paper tackles the high computational cost of ridge regression in high-dimensional classification by training an ensemble of ridge regressors in randomly projected subspaces and combining them with adaptive boosting, achieving reduced learning time and sometimes improved predictive performance across five high-dimensional datasets.
Ridge regression is a well established regression estimator which can conveniently be adapted for classification problems. One compelling reason is probably the fact that ridge regression emits a closed-form solution thereby facilitating the training phase. However in the case of high-dimensional problems, the closed-form solution which involves inverting the regularised covariance matrix is rather expensive to compute. The high computational demand of such operation also renders difficulty in constructing ensemble of ridge regressions. In this paper, we consider learning an ensemble of ridge regressors where each regressor is trained in its own randomly projected subspace. Subspace regressors are later combined via adaptive boosting methodology. Experiments based on five high-dimensional classification problems demonstrated the effectiveness of the proposed method in terms of learning time and in some cases improved predictive performance can be observed.