Convergence of a Generalized Gradient Selection Approach for the Decomposition Method
Abstract
The decomposition method is currently one of the major methods for solving the convex quadratic optimization problems being associated with support vector machines. For a special case of such problems the convergence of the decomposition method to an optimal solution has been proven based on a working set selection via the gradient of the objective function. In this paper we will show that a generalized version of the gradient selection approach and its associated decomposition algorithm can be used to solve a much broader class of convex quadratic optimization problems.
Cite
Text
List. "Convergence of a Generalized Gradient Selection Approach for the Decomposition Method." International Conference on Algorithmic Learning Theory, 2004. doi:10.1007/978-3-540-30215-5_26Markdown
[List. "Convergence of a Generalized Gradient Selection Approach for the Decomposition Method." International Conference on Algorithmic Learning Theory, 2004.](https://mlanthology.org/alt/2004/list2004alt-convergence/) doi:10.1007/978-3-540-30215-5_26BibTeX
@inproceedings{list2004alt-convergence,
title = {{Convergence of a Generalized Gradient Selection Approach for the Decomposition Method}},
author = {List, Nikolas},
booktitle = {International Conference on Algorithmic Learning Theory},
year = {2004},
pages = {338-349},
doi = {10.1007/978-3-540-30215-5_26},
url = {https://mlanthology.org/alt/2004/list2004alt-convergence/}
}