An augmented kernel ridge regression estimator separates linear and nonlinear components to achieve sharp oracle inequalities and minimax optimal prediction risk under general kernels.
arXiv preprint arXiv:2303.04020 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Derives high-probability excess risk bounds for Nyström-regularized learning under covariate shift in the misspecified low-smoothness case, with additional sample-size requirements when the Radon-Nikodym derivative is estimated.
citing papers explorer
-
Adaptive Kernel Ridge Regression with Linear Structure: Sharp Oracle Inequalities and Minimax Optimality
An augmented kernel ridge regression estimator separates linear and nonlinear components to achieve sharp oracle inequalities and minimax optimal prediction risk under general kernels.
-
Convergence Analysis of Nystr\"om Subsampling in Covariate Shift Adaptation for Misspecified case
Derives high-probability excess risk bounds for Nyström-regularized learning under covariate shift in the misspecified low-smoothness case, with additional sample-size requirements when the Radon-Nikodym derivative is estimated.