Pith. sign in

REVIEW 4 cited by

Neural Tangent Kernel: A Survey

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2208.13614 v1 pith:ZQ27C6X5 submitted 2022-08-29 cs.LG

Eugene Golikov , Eduard Pokonechnyy , Vladimir Korviakov This is my paper
classification cs.LG
keywords kernelneuralgoesinfinitymethodresultssurveywidth
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

A seminal work [Jacot et al., 2018] demonstrated that training a neural network under specific parameterization is equivalent to performing a particular kernel method as width goes to infinity. This equivalence opened a promising direction for applying the results of the rich literature on kernel methods to neural nets which were much harder to tackle. The present survey covers key results on kernel convergence as width goes to infinity, finite-width corrections, applications, and a discussion of the limitations of the corresponding method.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction

    eess.IV 2026-02 conditional novelty 6.0 of 10

    CogGen schedules MRI k-space measurements from low- to high-frequency during unsupervised reconstruction, reporting sharper images and faster convergence than prior methods.

  2. Efficient Adversarial Attacks on High-dimensional Offline Bandits

    cs.LG 2026-02 conditional novelty 6.0 of 10

    Perturbing the reward model's weights before offline bandit training can force UCB/ETC/epsilon-greedy to select a suboptimal arm, and the minimum perturbation norm decreases with input dimension.

  3. Learning to Execute Graph Algorithms Exactly with Graph Neural Networks

    cs.LG 2026-01 conditional novelty 6.0 of 10

    A GNN with an ensemble of MLPs can exactly execute any LOCAL-model graph algorithm after learning a polynomial-size set of local template instructions.

  4. Random at First, Fast at Last: NTK-Guided Fourier Pre-Processing for Tabular DL

    cs.LG 2025-06 conditional novelty 3.0 of 10

    Fixed random Fourier projections on tabular inputs are claimed to bound the NTK, speed up gradient descent, and improve accuracy across four architectures and eight benchmarks.

Pith tools