Introduces Label-NTK and Residual-NTK alignments to derive tighter NTK convergence bounds that track the full eigen-spectrum and match observed training speed.
Frequency bias in neural networks for input of non-uniform density
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Optimal INR freeze depth matches highest weight stable rank layer; SAEs reveal SIREN atoms are localized while FFMLP atoms trace cohort contours with causal impact on PSNR.
citing papers explorer
-
Label-NTK Alignments and A Tighter Convergence Bound in the NTK Regime
Introduces Label-NTK and Residual-NTK alignments to derive tighter NTK convergence bounds that track the full eigen-spectrum and match observed training speed.
-
What Cohort INRs Encode and Where to Freeze Them
Optimal INR freeze depth matches highest weight stable rank layer; SAEs reveal SIREN atoms are localized while FFMLP atoms trace cohort contours with causal impact on PSNR.