![](/images/graphics-bg.png)
Online Manifold Regularization by Dual Ascending Procedure
Joint Authors
Sun, Boliang
Li, Guohui
Jia, Li
Zhang, Hui
Source
Mathematical Problems in Engineering
Issue
Vol. 2013, Issue 2013 (31 Dec. 2013), pp.1-16, 16 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2013-07-07
Country of Publication
Egypt
No. of Pages
16
Main Subjects
Abstract EN
We propose a novel online manifold regularization framework based on the notion of duality in constrained optimization.
The Fenchel conjugate of hinge functions is a key to transfer manifold regularization from offline to online in this paper.
Our algorithms are derived by gradient ascent in the dual function.
For practical purpose, we propose two buffering strategies and two sparse approximations to reduce the computational complexity.
Detailed experiments verify the utility of our approaches.
An important conclusion is that our online MR algorithms can handle the settings where the target hypothesis is not fixed but drifts with the sequence of examples.
We also recap and draw connections to earlier works.
This paper paves a way to the design and analysis of online manifold regularization algorithms.
American Psychological Association (APA)
Sun, Boliang& Li, Guohui& Jia, Li& Zhang, Hui. 2013. Online Manifold Regularization by Dual Ascending Procedure. Mathematical Problems in Engineering،Vol. 2013, no. 2013, pp.1-16.
https://search.emarefa.net/detail/BIM-1010914
Modern Language Association (MLA)
Sun, Boliang…[et al.]. Online Manifold Regularization by Dual Ascending Procedure. Mathematical Problems in Engineering No. 2013 (2013), pp.1-16.
https://search.emarefa.net/detail/BIM-1010914
American Medical Association (AMA)
Sun, Boliang& Li, Guohui& Jia, Li& Zhang, Hui. Online Manifold Regularization by Dual Ascending Procedure. Mathematical Problems in Engineering. 2013. Vol. 2013, no. 2013, pp.1-16.
https://search.emarefa.net/detail/BIM-1010914
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1010914