Manifold mapping learning by regression tree boosting
Xi’ai Chen, Zhi Jun Han, Yandong Tang · 2015
Manifold learning has shown powerful information processing capability for high-dimensional data. In this paper, we proposed a manifold mapping learning algorithm to alleviate the shortage of traditional methods and broaden the applications of manifold learning. The mapping is achieved by using the regression tree boosting, which is a strong ensemble learner composed by a group of regression trees as weak learners in the way of L2Boost. A set of verification experiments are conducted on both synthetic and real-world data sets. And the results have demonstrated that the algorithm can perform well on both regression and prediction applications.