Journal of Applied Mathematics

Approximation Analysis of Gradient Descent Algorithm for Bipartite Ranking

Hong Chen, Fangchao He, and Zhibin Pan

Full-text: Open access

Abstract

We introduce a gradient descent algorithm for bipartite ranking with general convex losses. The implementation of this algorithm is simple, and its generalization performance is investigated. Explicit learning rates are presented in terms of the suitable choices of the regularization parameter and the step size. The result fills the theoretical gap in learning rates for ranking problem with general convex losses.

Article information

Source
J. Appl. Math., Volume 2012 (2012), Article ID 189753, 13 pages.

Dates
First available in Project Euclid: 14 December 2012

Permanent link to this document
https://projecteuclid.org/euclid.jam/1355495208

Digital Object Identifier
doi:10.1155/2012/189753

Mathematical Reviews number (MathSciNet)
MR2948147

Zentralblatt MATH identifier
1251.90314

Citation

Chen, Hong; He, Fangchao; Pan, Zhibin. Approximation Analysis of Gradient Descent Algorithm for Bipartite Ranking. J. Appl. Math. 2012 (2012), Article ID 189753, 13 pages. doi:10.1155/2012/189753. https://projecteuclid.org/euclid.jam/1355495208


Export citation