Boosting on Manifolds: Adaptive Regularization of Base Classifiers

In this paper we propose to combine two powerful ideas, boosting and manifold learning. On the one hand, we improve ADABOOST by incor- porating knowledge on the structure of the data into base classifier design and selection. On the other hand, we use ADABOOST's efficient learn- ing mechanism to significantly improve supervised and semi-supervised algorithms proposed in the context of manifold learning. Beside the spe- cific manifold-based penalization, the resulting algorithm also accommo- dates the boosting of a large family of regularized learning algorithms. ADABOOST [1] is one of the machine learning algorithms that have revolutionized pattern recognition technology in the last decade.