Pith. sign in

Kernel methods for deep learning // Advances in neural information processing systems

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

stat.ML 1

years

2025 1

verdicts

REJECT 1

representative citing papers

Issues with Neural Tangent Kernel Approach to Neural Networks

stat.ML · 2025-01-19 · reject · novelty 3.0

The paper reports numerical evidence that the NTK equivalence theorem does not hold for finite-width neural networks trained with SGD, because trained networks and NTK kernel regressors behave differently when a layer is added.

citing papers explorer

Showing 1 of 1 citing paper.

  • Issues with Neural Tangent Kernel Approach to Neural Networks stat.ML · 2025-01-19 · reject · none · ref 4

    The paper reports numerical evidence that the NTK equivalence theorem does not hold for finite-width neural networks trained with SGD, because trained networks and NTK kernel regressors behave differently when a layer is added.