Introduces Label-NTK and Residual-NTK alignments to derive tighter NTK convergence bounds that track the full eigen-spectrum and match observed training speed.
Neural tangent kernel: Convergence and generalization in neural networks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A dual representation of influence functions reduces computational cost from model size to dataset size for linearizable models.
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.
-
Extending Kernel Trick to Influence Functions
A dual representation of influence functions reduces computational cost from model size to dataset size for linearizable models.