Approximation Analysis of Gradient Descent Algorithm for Bipartite Ranking

Approximation Analysis of Gradient Descent Algorithm for Bipartite Ranking

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 t...

Full description

Bibliographic Details
Main Authors: Hong Chen, Fangchao He, Zhibin Pan
Format: Article
Language:English
Published: Hindawi Limited 2012-01-01
Series:Journal of Applied Mathematics
Online Access:http://dx.doi.org/10.1155/2012/189753
id doaj-9d0559f97bdc4dff96125ec0f9867b7c
record_format Article
spelling doaj-9d0559f97bdc4dff96125ec0f9867b7c2020-11-24T22:37:17ZengHindawi LimitedJournal of Applied Mathematics1110-757X1687-00422012-01-01201210.1155/2012/189753189753Approximation Analysis of Gradient Descent Algorithm for Bipartite RankingHong Chen0Fangchao He1Zhibin Pan2College of Science, Huazhong Agricultural University, Wuhan 430070, ChinaSchool of Science, Hubei University of Technology, Wuhan 430068, ChinaCollege of Science, Huazhong Agricultural University, Wuhan 430070, ChinaWe 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.http://dx.doi.org/10.1155/2012/189753
collection DOAJ
language English
format Article
sources DOAJ
author Hong Chen
Fangchao He
Zhibin Pan
spellingShingle Hong Chen
Fangchao He
Zhibin Pan
Approximation Analysis of Gradient Descent Algorithm for Bipartite Ranking
Journal of Applied Mathematics
author_facet Hong Chen
Fangchao He
Zhibin Pan
author_sort Hong Chen
title Approximation Analysis of Gradient Descent Algorithm for Bipartite Ranking
title_short Approximation Analysis of Gradient Descent Algorithm for Bipartite Ranking
title_full Approximation Analysis of Gradient Descent Algorithm for Bipartite Ranking
title_fullStr Approximation Analysis of Gradient Descent Algorithm for Bipartite Ranking
title_full_unstemmed Approximation Analysis of Gradient Descent Algorithm for Bipartite Ranking
title_sort approximation analysis of gradient descent algorithm for bipartite ranking
publisher Hindawi Limited
series Journal of Applied Mathematics
issn 1110-757X
1687-0042
publishDate 2012-01-01
description 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.
url http://dx.doi.org/10.1155/2012/189753
work_keys_str_mv AT hongchen approximationanalysisofgradientdescentalgorithmforbipartiteranking
AT fangchaohe approximationanalysisofgradientdescentalgorithmforbipartiteranking
AT zhibinpan approximationanalysisofgradientdescentalgorithmforbipartiteranking
_version_ 1725717689335283712

Similar Items