Introduces Label-NTK and Residual-NTK alignments to derive tighter NTK convergence bounds that track the full eigen-spectrum and match observed training speed.
Disentangling feature and lazy training in deep neural networks.Journal of Statistical Mechanics: Theory and Experiment, 2020(11):113301
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 2polarities
background 2representative citing papers
Online kernel regression equals offline regression with shifted targets; correcting the targets lets online learning match offline performance and outperform true targets in continual image classification.
A two-level DMFT tracks bulk and outlier spectral dynamics in wide networks, predicting width-consistent outlier growth and hyperparameter transfer under muP scaling for deep linear nets while noting bulk restructuring for large-output tasks.
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.
-
Characterizing and Correcting Effective Target Shift in Online Learning
Online kernel regression equals offline regression with shifted targets; correcting the targets lets online learning match offline performance and outperform true targets in continual image classification.
-
Spectral Dynamics in Deep Networks: Feature Learning, Outlier Escape, and Learning Rate Transfer
A two-level DMFT tracks bulk and outlier spectral dynamics in wide networks, predicting width-consistent outlier growth and hyperparameter transfer under muP scaling for deep linear nets while noting bulk restructuring for large-output tasks.