Speeding Up Greedy Forward Selection for Regularized Least-Squares

• Published in: 2010 International Conference on Machine Learning and Applications pp. 325 - 330
• Main Authors: Pahikkala, Tapio, Airola, Antti, Salakoski, Tapio
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.12.2010
• Subjects: Computational complexity; feature selection; greedy algorithm; least-squares support vector machine; Machine learning; Machine learning algorithms; Prediction algorithms; regularized least-squares; ridge regression; Training; Vectors

We propose a novel algorithm for greedy forward feature selection for regularized least-squares (RLS) regression and classification, also known as the least-squares support vector machine or ridge regression. The algorithm, which we call greedy RLS, starts from the empty feature set, and on each ite...