Introduces alignment-sensitive effective span dimension (ESD) for learned-kernel spectral algorithms and proves minimax excess risk bounds of order sigma^2 * ESD, with gradient flow shown to reduce ESD.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2025 2verdicts
UNVERDICTED 2representative citing papers
FEM decreases during training in linear regression and index models, providing supporting evidence for the adaptive feature program.
citing papers explorer
-
Alignment-Sensitive Minimax Rates for Spectral Algorithms with Learned Kernels
Introduces alignment-sensitive effective span dimension (ESD) for learned-kernel spectral algorithms and proves minimax excess risk bounds of order sigma^2 * ESD, with gradient flow shown to reduce ESD.
-
Supporting Evidence for the Adaptive Feature Program across Diverse Models
FEM decreases during training in linear regression and index models, providing supporting evidence for the adaptive feature program.