A Mathematical Programming Approach to the Kernel Fisher Algorithm
Abstract
We investigate a new kernel-based classifier: the Kernel Fisher Discrim(cid:173) inant (KFD). A mathematical programming formulation based on the ob(cid:173) servation that KFD maximizes the average margin permits an interesting modification of the original KFD algorithm yielding the sparse KFD. We find that both, KFD and the proposed sparse KFD, can be understood in an unifying probabilistic context. Furthermore, we show connections to Support Vector Machines and Relevance Vector Machines. From this understanding, we are able to outline an interesting kernel-regression technique based upon the KFD algorithm. Simulations support the use(cid:173) fulness of our approach.
Cite
Text
Mika et al. "A Mathematical Programming Approach to the Kernel Fisher Algorithm." Neural Information Processing Systems, 2000.Markdown
[Mika et al. "A Mathematical Programming Approach to the Kernel Fisher Algorithm." Neural Information Processing Systems, 2000.](https://mlanthology.org/neurips/2000/mika2000neurips-mathematical/)BibTeX
@inproceedings{mika2000neurips-mathematical,
title = {{A Mathematical Programming Approach to the Kernel Fisher Algorithm}},
author = {Mika, Sebastian and Rätsch, Gunnar and Müller, Klaus-Robert},
booktitle = {Neural Information Processing Systems},
year = {2000},
pages = {591-597},
url = {https://mlanthology.org/neurips/2000/mika2000neurips-mathematical/}
}