Proceedings of the 2016 International Conference on Applied Mathematics, Simulation and Modelling

The Relation of Solutions Between Different Models of Support Vector Regression

Authors
Meiqin Pan
Corresponding Author
Meiqin Pan
Available Online May 2016.
DOI
10.2991/amsm-16.2016.68How to use a DOI?
Keywords
quadratic rogramming; lagrange function; kkt condition
Abstract

The relations of solutions between different models of Support Vector Regression are proposed in this paper. Usually, Support Vector Regression (SVR) is formulated as a convex quadratic programming with bound constrains. With different improvements, different improved regression models and their strong convex programming have come into being. Basing on Lagrange function and KKT conditions, this paper proves strictly that the solution of improved model is the solution of prime model. Which provides the SVR with theory base.

Copyright
© 2016, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

Volume Title
Proceedings of the 2016 International Conference on Applied Mathematics, Simulation and Modelling
Series
Advances in Computer Science Research
Publication Date
May 2016
ISBN
978-94-6252-198-8
ISSN
2352-538X
DOI
10.2991/amsm-16.2016.68How to use a DOI?
Copyright
© 2016, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Cite this article

TY  - CONF
AU  - Meiqin Pan
PY  - 2016/05
DA  - 2016/05
TI  - The Relation of Solutions Between Different Models of Support Vector Regression
BT  - Proceedings of the 2016 International Conference on Applied Mathematics, Simulation and Modelling
PB  - Atlantis Press
SP  - 306
EP  - 309
SN  - 2352-538X
UR  - https://doi.org/10.2991/amsm-16.2016.68
DO  - 10.2991/amsm-16.2016.68
ID  - Pan2016/05
ER  -