An improved training algorithm for kernel Fisher discriminants

Sebastian Mika, Alexander J. Smola, Bernhard Schölkopf
Proceedings of the Eighth International Workshop on Artificial Intelligence and Statistics, PMLR R3:209-215, 2001.

Abstract

We present a fast training algorithm for the kernel Fisher discriminant classifier. It uses a greedy approximation technique and has an empirical scaling behavior which improves upon the state of the art by more than an order of magnitude, thus rendering the kernel Fisher algorithm a viable option also for large datasets.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR3-mika01a, title = {An improved training algorithm for kernel Fisher discriminants}, author = {Mika, Sebastian and Smola, Alexander J. and Sch{\"{o}}lkopf, Bernhard}, booktitle = {Proceedings of the Eighth International Workshop on Artificial Intelligence and Statistics}, pages = {209--215}, year = {2001}, editor = {Richardson, Thomas S. and Jaakkola, Tommi S.}, volume = {R3}, series = {Proceedings of Machine Learning Research}, month = {04--07 Jan}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/r3/mika01a/mika01a.pdf}, url = {https://proceedings.mlr.press/r3/mika01a.html}, abstract = {We present a fast training algorithm for the kernel Fisher discriminant classifier. It uses a greedy approximation technique and has an empirical scaling behavior which improves upon the state of the art by more than an order of magnitude, thus rendering the kernel Fisher algorithm a viable option also for large datasets.}, note = {Reissued by PMLR on 31 March 2021.} }
Endnote
%0 Conference Paper %T An improved training algorithm for kernel Fisher discriminants %A Sebastian Mika %A Alexander J. Smola %A Bernhard Schölkopf %B Proceedings of the Eighth International Workshop on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2001 %E Thomas S. Richardson %E Tommi S. Jaakkola %F pmlr-vR3-mika01a %I PMLR %P 209--215 %U https://proceedings.mlr.press/r3/mika01a.html %V R3 %X We present a fast training algorithm for the kernel Fisher discriminant classifier. It uses a greedy approximation technique and has an empirical scaling behavior which improves upon the state of the art by more than an order of magnitude, thus rendering the kernel Fisher algorithm a viable option also for large datasets. %Z Reissued by PMLR on 31 March 2021.
APA
Mika, S., Smola, A.J. & Schölkopf, B.. (2001). An improved training algorithm for kernel Fisher discriminants. Proceedings of the Eighth International Workshop on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research R3:209-215 Available from https://proceedings.mlr.press/r3/mika01a.html. Reissued by PMLR on 31 March 2021.

Related Material