Convergence Analysis of an Empirical Eigenfunction-Based Ranking Algorithm with Truncated Sparsity. (20th July 2014)

• Record Type: Journal Article
• Authors: Xu, Min; Fang, Qin; Wang, Shaofan
• Other Names: Pereverzyev Sergei V. Academic Editor.
• Is Part Of: Abstract and applied analysis. Volume 2014(2014)
• Publication Date: 2014-07-20
• Subjects: Mathematical analysis -- Periodicals; Mathematical analysis; Applied Mathematics; Mathematical Analysis; Periodicals; 515.05
• DOI: 10.1155/2014/197476
• Languages: English
• ISSNs: 1085-3375

Abstract

Abstract : We study an empirical eigenfunction-based algorithm for ranking with a data dependent hypothesis space. The space is spanned by certain empirical eigenfunctions which we select by using a truncated parameter. We establish the representer theorem and convergence analysis of the algorithm. In particular, we show that under a mild condition, the algorithm produces a satisfactory convergence rate as well as sparse representations with respect to the empirical eigenfunctions.