Hong Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Hong Chen has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Luoqing Li
Faculty of Mathematics and Statistics, Hubei University, Wuhan, China
6 shared publications - Jiangtao Peng
Hubei University
2 shared publications - Yicong Zhou
University of Macau
2 shared publications Zhibin Pan
2 shared publicationsFangchao He
School of Science, Hubei University of Technology, Wuhan 430068, China
1 shared publicationLuoqing Li
1 shared publication
Latest Publications
- 1 May 2014
- Published by Elsevier in Neural Networks
- Vol. 53, 119-126
Extreme learning machine for ranking: Generalization analysis and applications
- 1 May 2014
- Published by Elsevier in Neural Networks
- Vol. 53, 119-126
Extreme learning machine for ranking: Generalization analysis and applications
- 1 August 2013
- Published by Elsevier in Neural Networks
- Vol. 44, 44-50
Convergence rate of the semi-supervised greedy algorithm
- 1 August 2013
- Published by Elsevier in Neural Networks
- Vol. 44, 44-50
Convergence rate of the semi-supervised greedy algorithm
- Open Access
- 1 January 2012
- Published by Wiley in Journal of Applied Mathematics
- Vol. 2012 (1)
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 the step size. The result fills the theoretical gap in learning rates for ranking problem with general convex losses.
- 1 January 2012
- Published by Wiley in Journal of Applied Mathematics
- Vol. 2012 (1)
Open AccessApproximation 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 the step size. The result fills the theoretical gap in learning rates for ranking problem with general convex losses.
- 1 September 2010
- Published by Elsevier in Neural Networks
- Vol. 23 (7) , 812-818
Semi-supervised learning based on high density region estimation
- 1 September 2010
- Published by Elsevier in Neural Networks
- Vol. 23 (7) , 812-818
Semi-supervised learning based on high density region estimation
- 1 November 2009
- Published by Springer Nature in Science China Mathematics
- Vol. 52 (11) , 2506-2516
Generalization performance of graph-based semi-supervised classification
- 1 November 2009
- Published by Springer Nature in Science China Mathematics
- Vol. 52 (11) , 2506-2516
Generalization performance of graph-based semi-supervised classification
- 28 August 2009
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 20 (10) , 1594-1603
Semisupervised Multicategory Classification With Imperfect Model
Semisupervised learning has been of growing interest over the past years and many methods have been proposed. While existing semisupervised methods have shown some promising empirical performances, their development has been based largely on heuristics. In this paper, we investigate semisupervised multicategory classification with an imperfect mixture density model. In the proposed model, the training data come from a probability distribution, which can be modeled imperfectly by an identifiable mixture distribution. Furthermore, we propose a semisupervised multicategory classification method and establish its generalization error bounds. The theoretical analysis illustrates that the proposed method can utilize unlabeled data effectively and can achieve fast convergence rate.
- 28 August 2009
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 20 (10) , 1594-1603
Semisupervised Multicategory Classification With Imperfect Model
Semisupervised learning has been of growing interest over the past years and many methods have been proposed. While existing semisupervised methods have shown some promising empirical performances, their development has been based largely on heuristics. In this paper, we investigate semisupervised multicategory classification with an imperfect mixture density model. In the proposed model, the training data come from a probability distribution, which can be modeled imperfectly by an identifiable mixture distribution. Furthermore, we propose a semisupervised multicategory classification method and establish its generalization error bounds. The theoretical analysis illustrates that the proposed method can utilize unlabeled data effectively and can achieve fast convergence rate.
- 31 July 2007
- Published by Springer Nature in Science China Mathematics
- Vol. 50 (11) , 1529-1536
On the rate of convergence for multi-category classification based on convex losses
- 31 July 2007
- Published by Springer Nature in Science China Mathematics
- Vol. 50 (11) , 1529-1536
On the rate of convergence for multi-category classification based on convex losses
- 1 June 2007
- Published by Springer Nature in Analysis in Theory and Applications
- Vol. 23 (2) , 188-195
Generalization performance of multi-category kernel machines
- 1 June 2007
- Published by Springer Nature in Analysis in Theory and Applications
- Vol. 23 (2) , 188-195
Generalization performance of multi-category kernel machines