Fixed-bandwidth Gaussian kernels let any spectral algorithm achieve minimax nonparametric rates, and the resulting two-stage procedure attains near-optimal transfer learning under concept shift.
Optimal rates for regularization of statistical inverse learning problems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Fixed-Gaussian Spectral Algorithms: Minimax Optimal Rates for Misspecified Learning and Transfer
Fixed-bandwidth Gaussian kernels let any spectral algorithm achieve minimax nonparametric rates, and the resulting two-stage procedure attains near-optimal transfer learning under concept shift.