Error bounds for Kernel Fisher Linear Discriminant in Gaussian Hilbert space

Robert Durrant, Ata Kaban
; Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, PMLR 22:337-345, 2012.

Abstract

We give a non-trivial, non-asymptotic upper bound on the classification error of the popular Kernel Fisher Linear Discriminant classifier under the assumption that the kernel-induced space is a Gaussian Hilbert space.

Cite this Paper


BibTeX
@InProceedings{pmlr-v22-durrant12, title = {Error bounds for Kernel Fisher Linear Discriminant in Gaussian Hilbert space}, author = {Robert Durrant and Ata Kaban}, booktitle = {Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics}, pages = {337--345}, year = {2012}, editor = {Neil D. Lawrence and Mark Girolami}, volume = {22}, series = {Proceedings of Machine Learning Research}, address = {La Palma, Canary Islands}, month = {21--23 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v22/durrant12/durrant12.pdf}, url = {http://proceedings.mlr.press/v22/durrant12.html}, abstract = {We give a non-trivial, non-asymptotic upper bound on the classification error of the popular Kernel Fisher Linear Discriminant classifier under the assumption that the kernel-induced space is a Gaussian Hilbert space.} }
Endnote
%0 Conference Paper %T Error bounds for Kernel Fisher Linear Discriminant in Gaussian Hilbert space %A Robert Durrant %A Ata Kaban %B Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2012 %E Neil D. Lawrence %E Mark Girolami %F pmlr-v22-durrant12 %I PMLR %J Proceedings of Machine Learning Research %P 337--345 %U http://proceedings.mlr.press %V 22 %W PMLR %X We give a non-trivial, non-asymptotic upper bound on the classification error of the popular Kernel Fisher Linear Discriminant classifier under the assumption that the kernel-induced space is a Gaussian Hilbert space.
RIS
TY - CPAPER TI - Error bounds for Kernel Fisher Linear Discriminant in Gaussian Hilbert space AU - Robert Durrant AU - Ata Kaban BT - Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics PY - 2012/03/21 DA - 2012/03/21 ED - Neil D. Lawrence ED - Mark Girolami ID - pmlr-v22-durrant12 PB - PMLR SP - 337 DP - PMLR EP - 345 L1 - http://proceedings.mlr.press/v22/durrant12/durrant12.pdf UR - http://proceedings.mlr.press/v22/durrant12.html AB - We give a non-trivial, non-asymptotic upper bound on the classification error of the popular Kernel Fisher Linear Discriminant classifier under the assumption that the kernel-induced space is a Gaussian Hilbert space. ER -
APA
Durrant, R. & Kaban, A.. (2012). Error bounds for Kernel Fisher Linear Discriminant in Gaussian Hilbert space. Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, in PMLR 22:337-345

Related Material