Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

December 2006, Vol. 18, No. 12, Pages 2928-2935
(doi: 10.1162/neco.2006.18.12.2928)
© 2006 Massachusetts Institute of Technology
Kernel Least-Squares Models Using Updates of the Pseudoinverse
Article PDF (68.2 KB)
Abstract

Sparse nonlinear classification and regression models in reproducing kernel Hilbert spaces (RKHSs) are considered. The use of Mercer kernels and the square loss function gives rise to an overdetermined linear least-squares problem in the corresponding RKHS. When we apply a greedy forward selection scheme, the least-squares problem may be solved by an order-recursive update of the pseudoinverse in each iteration step. The computational time is linear with respect to the number of the selected training samples.