Derives a finite-sample generalization bound for KRR by analyzing how perturbations in the kernel matrix affect eigenvector and eigenvalue estimates, concluding that reconstruction error has limited value for high-rank kernels.
A support vector machine with a hybrid kernel and minimal vapnik-chervonenkis dimension
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
On Kernel Eigen-alignments of KRR: Reconstruction and Generalization
Derives a finite-sample generalization bound for KRR by analyzing how perturbations in the kernel matrix affect eigenvector and eigenvalue estimates, concluding that reconstruction error has limited value for high-rank kernels.