Methods › General › Kernel Methods › NTK
Neural Tangent Kernel
NTK
Introduced by Arthur Jacot et al. in Neural Tangent Kernel: Convergence and Generalization in Neural Networks
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
The archive carries no description for this method.
In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.
Near matches the lookup lists, each a different name: FL-NTK; Adv-NTK; NTK-KIP; trace NTK; NTK-Selector; NTK-UQ pipeline; Label-NTK Alignments; Convolutional NTK (CNTK).
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 233 · with a code link: 72 · where Syntology ran a sample: 35 (25 with a run with no instrument failure, 10 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (35 of 233 tagged: 25 with a run with no instrument failure, 10 where every run was a failure of Syntology's instrument)
Page 1 of 3: papers 1 to 100 of 233, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
Neural Tangent Kernel Analysis to Probe Convergence in Physics-informed Neural Solvers: PIKANs vs. PINNs 9 Jun 2025 · 0 repositories · arXiv:2506.07958
-
GradPCA: Leveraging NTK Alignment for Reliable Out-of-Distribution Detection 21 May 2025 · 0 repositories · arXiv:2505.16017
-
Just One Layer Norm Guarantees Stable Extrapolation 20 May 2025 · 0 repositories · arXiv:2505.14512
-
Training NTK to Generalize with KARE 16 May 2025 · 2 repositories · arXiv:2505.11347
-
Precise gradient descent training dynamics for finite-width multi-layer neural networks 8 May 2025 · 0 repositories · arXiv:2505.04898
-
How Learnable Grids Recover Fine Detail in Low Dimensions: A Neural Tangent Kernel Analysis of Multigrid Parametric Encodings 18 Apr 2025 · 0 repositories · arXiv:2504.13412
-
Divergence of Empirical Neural Tangent Kernel in Classification Problems 15 Apr 2025 · 0 repositories · arXiv:2504.11130
-
Neural Tangent Kernel of Neural Networks with Loss Informed by Differential Operators 14 Mar 2025 · 0 repositories · arXiv:2503.11029
-
Determinant Estimation under Memory Constraints and Neural Scaling Laws 6 Mar 2025 · 1 repository · arXiv:2503.04424
-
MLPs at the EOC: Concentration of the NTK 24 Jan 2025 · 0 repositories · arXiv:2501.14724
-
MLPs at the EOC: Spectrum of the NTK 22 Jan 2025 · 0 repositories · arXiv:2501.13225
-
Issues with Neural Tangent Kernel Approach to Neural Networks 19 Jan 2025 · 1 repository · arXiv:2501.10929
-
Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories 25 Dec 2024 · 0 repositories · arXiv:2412.18756
-
Optimal Convergence Rates for Neural Operators 23 Dec 2024 · 0 repositories · arXiv:2412.17518
-
Is the neural tangent kernel of PINNs deep learning general partial differential equations always convergent ? 9 Dec 2024 · 0 repositories · arXiv:2412.06158
-
Exact Certification of (Graph) Neural Networks Against Label Poisoning 30 Nov 2024 · 1 repository · arXiv:2412.00537Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
Infinite Width Limits of Self Supervised Neural Networks 17 Nov 2024 · 0 repositories · arXiv:2411.11176
-
Gradient Descent Finds Over-Parameterized Neural Networks with Sharp Generalization for Nonparametric Regression 5 Nov 2024 · 0 repositories · arXiv:2411.02904
-
Sharper Guarantees for Learning Neural Network Classifiers with Gradient Methods 13 Oct 2024 · 0 repositories · arXiv:2410.10024
-
Collective variables of neural networks: empirical time evolution and scaling laws 9 Oct 2024 · 0 repositories · arXiv:2410.07451
-
On the Impacts of the Random Initialization in the Neural Tangent Kernel Theory 8 Oct 2024 · 0 repositories · arXiv:2410.05626
-
Correlation-Aware Select and Merge Attention for Efficient Fine-Tuning and Context Length Extension 5 Oct 2024 · 0 repositories · arXiv:2410.04211
-
NTK-DFL: Enhancing Decentralized Federated Learning in Heterogeneous Settings via Neural Tangent Kernel 2 Oct 2024 · 0 repositories · arXiv:2410.01922
-
How Feature Learning Can Improve Neural Scaling Laws 26 Sep 2024 · 0 repositories · arXiv:2409.17858
-
Parameter-Efficient Fine-Tuning for Continual Learning: A Neural Tangent Kernel Perspective 24 Jul 2024 · 0 repositories · arXiv:2407.17120
-
Differential Privacy Mechanisms in Neural Tangent Kernel Regression 18 Jul 2024 · 0 repositories · arXiv:2407.13621
-
Preconditioned Gradient Descent Finds Over-Parameterized Neural Networks with Sharp Generalization for Nonparametric Regression 16 Jul 2024 · 0 repositories · arXiv:2407.11353
-
Stochastic Gradient Descent for Two-layer Neural Networks 10 Jul 2024 · 0 repositories · arXiv:2407.07670
-
Training Guarantees of Neural Network Classification Two-Sample Tests by Kernel Analysis 5 Jul 2024 · 1 repository · arXiv:2407.04806
-
Infinite Width Models That Work: Why Feature Learning Doesn't Matter as Much as You Think 27 Jun 2024 · 0 repositories · arXiv:2406.18800
-
Can Kernel Methods Explain How the Data Affects Neural Collapse? 4 Jun 2024 · 1 repository · arXiv:2406.02105Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
How Does Gradient Descent Learn Features -- A Local Analysis for Regularized Two-Layer Neural Networks 3 Jun 2024 · 0 repositories · arXiv:2406.01766
-
Understanding Linear Probing then Fine-tuning Language Models from NTK Perspective 27 May 2024 · 1 repository · arXiv:2405.16747Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)
-
A generalized neural tangent kernel for surrogate gradient learning 24 May 2024 · 0 repositories · arXiv:2405.15539
-
When Foresight Pruning Meets Zeroth-Order Optimization: Efficient Federated Learning for Low-Memory Devices 8 May 2024 · 0 repositories · arXiv:2405.04765
-
Exploring the Frontiers of Softmax: Provable Optimization, Applications in Diffusion Model, and Beyond 6 May 2024 · 0 repositories · arXiv:2405.03251
-
HOIN: High-Order Implicit Neural Representations 23 Apr 2024 · 0 repositories · arXiv:2404.14674
-
The Positivity of the Neural Tangent Kernel 19 Apr 2024 · 0 repositories · arXiv:2404.12928
-
LongEmbed: Extending Embedding Models for Long Context Retrieval 18 Apr 2024 · 1 repository · arXiv:2404.12096Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified (of 6 harvested samples) · 6 pointer-only (licence)
-
Demystifying Lazy Training of Neural Networks from a Macroscopic Viewpoint 7 Apr 2024 · 0 repositories · arXiv:2404.04859
-
A Unified Kernel for Neural Network Learning 26 Mar 2024 · 0 repositories · arXiv:2403.17467
-
NTK-Guided Few-Shot Class Incremental Learning 19 Mar 2024 · 1 repository · arXiv:2403.12486
-
When Training-Free NAS Meets Vision Transformer: A Neural Tangent Kernel Perspective 15 Mar 2024 · 0 repositories · arXiv:2405.04536
-
When can we Approximate Wide Contrastive Models with Neural Tangent Kernels and Principal Component Analysis? 13 Mar 2024 · 0 repositories · arXiv:2403.08673
-
"Lossless" Compression of Deep Neural Networks: A High-dimensional Neural Tangent Kernel Approach 1 Mar 2024 · 1 repository · arXiv:2403.00258Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 8 harvested samples)
-
Super Consistency of Neural Network Landscapes and Learning Rate Transfer 27 Feb 2024 · 0 repositories · arXiv:2402.17457
-
Analyzing the Neural Tangent Kernel of Periodically Activated Coordinate Networks 7 Feb 2024 · 0 repositories · arXiv:2402.04783
-
The Challenges of the Nonlinear Regime for Physics-Informed Neural Networks 6 Feb 2024 · 0 repositories · arXiv:2402.03864
-
Deep Equilibrium Models are Almost Equivalent to Not-so-deep Explicit Models for High-dimensional Gaussian Mixtures 5 Feb 2024 · 1 repository · arXiv:2402.02697Syntology official (archive's flag): 11 ran · 11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 4 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified (of 14 harvested samples) · 14 pointer-only (licence)
-
PINN-BO: A Black-box Optimization Algorithm using Physics-Informed Neural Networks 5 Feb 2024 · 0 repositories · arXiv:2402.03243
-
Rethinking Adversarial Training with Neural Tangent Kernel 4 Dec 2023 · 0 repositories · arXiv:2312.02236
-
Efficient kernel surrogates for neural network-based regression 28 Oct 2023 · 0 repositories · arXiv:2310.18612
-
On the Neural Tangent Kernel of Equilibrium Models 21 Oct 2023 · 0 repositories · arXiv:2310.14062
-
Neural Tangent Kernels Motivate Graph Neural Networks with Cross-Covariance Graphs 16 Oct 2023 · 0 repositories · arXiv:2310.10791
-
Feature Learning and Generalization in Deep Networks with Orthogonal Weights 11 Oct 2023 · 0 repositories · arXiv:2310.07765
-
On the Convergence of Federated Averaging under Partial Participation for Over-parameterized Neural Networks 9 Oct 2023 · 0 repositories · arXiv:2310.05495
-
On the Disconnect Between Theory and Practice of Neural Networks: Limits of the NTK Perspective 29 Sep 2023 · 0 repositories · arXiv:2310.00137
-
Fixing the NTK: From Neural Network Linearizations to Exact Convex Programs 26 Sep 2023 · 0 repositories · arXiv:2309.15096
-
Convolutional Deep Kernel Machines 18 Sep 2023 · 1 repository · arXiv:2309.09814Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
How many Neurons do we need? A refined Analysis for Shallow Networks trained with Gradient Descent 14 Sep 2023 · 0 repositories · arXiv:2309.08044
-
Is Solving Graph Neural Tangent Kernel Equivalent to Training Graph Neural Network? 14 Sep 2023 · 0 repositories · arXiv:2309.07452
-
Approximation Results for Gradient Descent trained Neural Networks 9 Sep 2023 · 0 repositories · arXiv:2309.04860
-
Connecting NTK and NNGP: A Unified Theoretical Framework for Wide Neural Network Learning Dynamics 8 Sep 2023 · 0 repositories · arXiv:2309.04522
-
An Exact Kernel Equivalence for Finite Classification Models 1 Aug 2023 · 0 repositories · arXiv:2308.00824
-
Speed Limits for Deep Learning 27 Jul 2023 · 0 repositories · arXiv:2307.14653
-
MLP Fusion: Towards Efficient Fine-tuning of Dense and Mixture-of-Experts Language Models 18 Jul 2023 · 1 repository · arXiv:2307.08941Syntology official (archive's flag): 10 ran · 10 ran (of which 5 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified (of 14 harvested samples) · 14 pointer-only (licence)
-
Kernels, Data & Physics 5 Jul 2023 · 0 repositories · arXiv:2307.02693
-
Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time 28 Jun 2023 · 0 repositories · arXiv:2306.16361
-
NTKCPL: Active Learning on Top of Self-Supervised Model by Estimating True Coverage 7 Jun 2023 · 0 repositories · arXiv:2306.04099
-
Benign Overfitting in Deep Neural Networks under Lazy Training 30 May 2023 · 0 repositories · arXiv:2305.19377
-
Bottleneck Structure in Learned Features: Low-Dimension vs Regularity Tradeoff 30 May 2023 · 0 repositories · arXiv:2305.19008
-
Neural (Tangent Kernel) Collapse 25 May 2023 · 0 repositories · arXiv:2305.16427
-
Faithful and Efficient Explanations for Neural Networks via Neural Tangent Kernel Surrogate Models 23 May 2023 · 1 repository · arXiv:2305.14585Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models 22 May 2023 · 1 repository · arXiv:2305.12827Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 4 harvested samples) · 3 pointer-only (licence)
-
Tight conditions for when the NTK approximation is valid 22 May 2023 · 0 repositories · arXiv:2305.13141
-
How Spurious Features Are Memorized: Precise Analysis for Random and NTK Features 20 May 2023 · 1 repository · arXiv:2305.12100
-
ReLU soothes the NTK condition number and accelerates optimization for wide neural networks 15 May 2023 · 0 repositories · arXiv:2305.08813
-
On the Eigenvalue Decay Rates of a Class of Neural-Network Related Kernel Functions Defined on General Domains 4 May 2023 · 0 repositories · arXiv:2305.02657
-
Towards a Phenomenological Understanding of Neural Networks: Data 1 May 2023 · 0 repositories · arXiv:2305.00995
-
NTK-SAP: Improving neural network pruning by aligning training dynamics 6 Apr 2023 · 1 repository · arXiv:2304.02840Syntology official: harvested, nothing ran · 0 ran · 2 unverified (of 2 harvested samples)
-
Wide neural networks: From non-gaussian random fields at initialization to the NTK geometry of training 6 Apr 2023 · 0 repositories · arXiv:2304.03385
-
Neural-BO: A Black-box Optimization Algorithm using Deep Neural Networks 3 Mar 2023 · 1 repository · arXiv:2303.01682
-
Generalization Ability of Wide Neural Networks on ℝ 12 Feb 2023 · 0 repositories · arXiv:2302.05933
-
Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent Kernels 3 Feb 2023 · 1 repository · arXiv:2302.01629Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
Over-parameterised Shallow Neural Networks with Asymmetrical Node Scaling: Global Convergence Guarantees and Feature Learning 2 Feb 2023 · 1 repository · arXiv:2302.01002
-
Gradient Descent in Neural Networks as Sequential Learning in RKBS 1 Feb 2023 · 0 repositories · arXiv:2302.00205
-
Graph Neural Tangent Kernel: Convergence on Large Graphs 25 Jan 2023 · 0 repositories · arXiv:2301.10808
-
Expected Gradients of Maxout Networks and Consequences to Parameter Initialization 17 Jan 2023 · 1 repository · arXiv:2301.06956
-
Understanding the Spectral Bias of Coordinate Based MLPs Via Training Dynamics 14 Jan 2023 · 0 repositories · arXiv:2301.05816
-
Neural Networks with Sparse Activation Induced by Large Bias: Tighter Analysis with Bias-Generalized NTK 1 Jan 2023 · 0 repositories · arXiv:2301.00327
-
The Onset of Variance-Limited Behavior for Networks in the Lazy and Rich Regimes 23 Dec 2022 · 1 repository · arXiv:2212.12147Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
Graph Neural Networks are Inherently Good Generalizers: Insights by Bridging GNNs and MLPs 18 Dec 2022 · 1 repository · arXiv:2212.09034Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
Nonlinear Advantage: Trained Networks Might Not Be As Complex as You Think 30 Nov 2022 · 0 repositories · arXiv:2211.17180
-
Understanding Sparse Feature Updates in Deep Networks using Iterative Linearisation 22 Nov 2022 · 0 repositories · arXiv:2211.12345
-
Neural tangent kernel analysis of PINN for advection-diffusion equation 21 Nov 2022 · 0 repositories · arXiv:2211.11716
-
Characterizing the Spectrum of the NTK via a Power Series Expansion 15 Nov 2022 · 1 repository · arXiv:2211.07844Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
Evolution of Neural Tangent Kernels under Benign and Adversarial Training 21 Oct 2022 · 1 repository · arXiv:2210.12030
-
Sample-Then-Optimize Batch Neural Thompson Sampling 13 Oct 2022 · 1 repository · arXiv:2210.06850Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
A Kernel-Based View of Language Model Fine-Tuning 11 Oct 2022 · 1 repository · arXiv:2210.05643Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 7 harvested samples) · 1 pointer-only (licence)
-
What Can the Neural Tangent Kernel Tell Us About Adversarial Robustness? 11 Oct 2022 · 1 repository · arXiv:2210.05577
Tasks archive 2025-07-28
20 shown of 102 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections