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.
Capacity of reproducing kernel spaces in learning theory
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 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.