Multi-Prototype Support Vector Machine
Abstract
We extend multiclass SVM to multiple prototypes per class. For this framework, we give a compact constrained quadratic problem and we suggest an efficient algorithm for its optimization that guarantees a local minimum of the objective function. An annealed process is also proposed that helps to escape from local minima. Finally, we report experiments where the performance obtained using linear models is almost comparable to that obtained by state-of-art kernel-based methods but with a significant reduction (of one or two orders) in response time. 1
Cite
Text
Aiolli and Sperduti. "Multi-Prototype Support Vector Machine." International Joint Conference on Artificial Intelligence, 2003.Markdown
[Aiolli and Sperduti. "Multi-Prototype Support Vector Machine." International Joint Conference on Artificial Intelligence, 2003.](https://mlanthology.org/ijcai/2003/aiolli2003ijcai-multi/)BibTeX
@inproceedings{aiolli2003ijcai-multi,
title = {{Multi-Prototype Support Vector Machine}},
author = {Aiolli, Fabio and Sperduti, Alessandro},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2003},
pages = {541-546},
url = {https://mlanthology.org/ijcai/2003/aiolli2003ijcai-multi/}
}