TY  - JOUR
A1  - Gnecco, Giorgio
A1  - Sanguineti, Marcello
PB  - Springer
SP  - 197
Y1  - 2010///
IS  - 2
JF  - Optimization Letters
VL  - 4
SN  - 1862-4472
N2  - Suboptimal solutions to kernel principal component analysis are considered. Such solutions take on the form of linear combinations of all n-tuples of kernel functions centered on the data, where n is a positive integer smaller than the cardinality m of the data sample. Their accuracy in approximating the optimal solution, obtained in general for n = m, is estimated. The analysis made in Gnecco and Sanguineti (Comput Optim Appl 42:265?287, 2009) is extended. The estimates derived therein for the approximation of the first principal axis are improved and extensions to the successive principal axes are derived.
TI  - Error bounds for suboptimal solutions to kernel principal component analysis
AV  - none
KW  - Principal component analysis (PCA); Kernel methods; Suboptimal solutions
UR  - http://dx.doi.org/10.1007/s11590-009-0158-1
ID  - eprints1710
EP  - 210
ER  -