Efficient leave-one-out cross-validation of kernel fisher discriminant classifiers

Gavin C. Cawley, Nicola L.C. Talbot
2003 Pattern Recognition  
Mika et al. (in: Neural Network for Signal Processing, Vol. IX, IEEE Press, New York, 1999; pp. 41-48) apply the "kernel trick" to obtain a non-linear variant of Fisher's linear discriminant analysis method, demonstrating state-of-the-art performance on a range of benchmark data sets. We show that leave-one-out cross-validation of kernel Fisher discriminant classiÿers can be implemented with a computational complexity of only O(' 3 ) operations rather than the O(' 4 ) of a na ve implementation,
more » ... where ' is the number of training patterns. Leave-one-out cross-validation then becomes an attractive means of model selection in large-scale applications of kernel Fisher discriminant analysis, being signiÿcantly faster than conventional k-fold cross-validation procedures commonly used.
doi:10.1016/s0031-3203(03)00136-5 fatcat:dzuueoby6vamtnv6nv2b4hi2aq