Dynamic regret bounds for online kernel regression are obtained by running ensembles of discounted VAW forecasters on orthogonal subspace approximations of the RKHS, with explicit constructions for Gaussian, analytic, Mercer, and Matérn kernels.
Sobolev Bounds on Functions with Scattered Zeros, with Applications to Radial Basis Function Surface Fitting
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Dynamic Regret for Online Regression in RKHS via Discounted VAW and Subspace Approximation
Dynamic regret bounds for online kernel regression are obtained by running ensembles of discounted VAW forecasters on orthogonal subspace approximations of the RKHS, with explicit constructions for Gaussian, analytic, Mercer, and Matérn kernels.