Alternating direction method of multipliers for regularized multiclass support vector machines

Yangyang Xu Ioannis Akrotirianakis Amit Chakraborty

Optimization and Control mathscidoc:1912.43156

105-117, 2015.7
The support vector machine (SVM) was originally designed for binary classifications. A lot of effort has been put to generalize the binary SVM to multiclass SVM (MSVM) which are more complex problems. Initially, MSVMs were solved by considering their dual formulations which are quadratic programs and can be solved by standard second-order methods. However, the duals of MSVMs with regularizers are usually more difficult to formulate and computationally very expensive to solve. This paper focuses on several regularized MSVMs and extends the alternating direction method of multiplier (ADMM) to these MSVMs. Using a splitting technique, all considered MSVMs are written as two-block convex programs, for which the ADMM has global convergence guarantees. Numerical experiments on synthetic and real data demonstrate the high efficiency and accuracy of our algorithms.
No keywords uploaded!
[ Download ] [ 2019-12-21 11:26:22 uploaded by Yangyang_Xu ] [ 202 downloads ] [ 0 comments ]
@inproceedings{yangyang2015alternating,
  title={Alternating direction method of multipliers for regularized multiclass support vector machines},
  author={Yangyang Xu, Ioannis Akrotirianakis, and Amit Chakraborty},
  url={http://archive.ymsc.tsinghua.edu.cn/pacm_paperurl/20191221112622418489716},
  pages={105-117},
  year={2015},
}
Yangyang Xu, Ioannis Akrotirianakis, and Amit Chakraborty. Alternating direction method of multipliers for regularized multiclass support vector machines. 2015. pp.105-117. http://archive.ymsc.tsinghua.edu.cn/pacm_paperurl/20191221112622418489716.
Please log in for comment!
 
 
Contact us: office-iccm@tsinghua.edu.cn | Copyright Reserved