Methods › General › Kernel Methods › NTK › Papers, page 2

Neural Tangent Kernel

NTK

Papers archive 2025-07-28

archive papers tagged: 233 · with a code link: 72 · where Syntology ran a sample: 35 (26 with a run with no instrument failure, 9 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (35 of 233 tagged: 26 with a run with no instrument failure, 9 where every run was a failure of Syntology's instrument)

Page 2 of 3: papers 101 to 200 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.

• Efficient NTK using Dimensionality Reduction
  10 Oct 2022 · 0 repositories · arXiv:2210.04807
• Second-order regression models exhibit progressive sharpening to the edge of stability
  10 Oct 2022 · 0 repositories · arXiv:2210.04860
• The Influence of Learning Rule on Representation Dynamics in Wide Neural Networks
  5 Oct 2022 · 0 repositories · arXiv:2210.02157
• Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study
  16 Sep 2022 · 0 repositories · arXiv:2209.07736
• Generalization Properties of NAS under Activation and Skip Connection Search
  15 Sep 2022 · 0 repositories · arXiv:2209.07238
• Fast Neural Kernel Embeddings for General Activations
  9 Sep 2022 · 2 repositories · arXiv:2209.04121
  Syntology 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)
• Feature selection with gradient descent on two-layer networks in low-rotation regimes
  4 Aug 2022 · 0 repositories · arXiv:2208.02789
• Single Model Uncertainty Estimation via Stochastic Data Centering
  14 Jul 2022 · 1 repository · arXiv:2207.07235
  Syntology 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)
• Out of Distribution Detection via Neural Network Anchoring
  8 Jul 2022 · 3 repositories · arXiv:2207.04125
• Neural Stein critics with staged L²-regularization
  7 Jul 2022 · 1 repository · arXiv:2207.03406
• Limitations of the NTK for Understanding Generalization in Deep Learning
  20 Jun 2022 · 0 repositories · arXiv:2206.10012
• Fast Finite Width Neural Tangent Kernel
  17 Jun 2022 · 2 repositories · arXiv:2206.08720
  Syntology 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) · 2 unverified (of 3 harvested samples)
• Large-width asymptotics for ReLU neural networks with α-Stable initializations
  16 Jun 2022 · 0 repositories · arXiv:2206.08065
• Why Quantization Improves Generalization: NTK of Binary Weight Neural Networks
  13 Jun 2022 · 0 repositories · arXiv:2206.05916
• Identifying good directions to escape the NTK regime and efficiently learn low-degree plus sparse polynomials
  8 Jun 2022 · 1 repository · arXiv:2206.03688
• On the Generalization Power of the Overfitted Three-Layer Neural Tangent Kernel Model
  4 Jun 2022 · 0 repositories · arXiv:2206.02047
• Infinite Recommendation Networks: A Data-Centric Approach
  3 Jun 2022 · 5 repositories · arXiv:2206.02626
  Syntology official (archive's flag): 5 ran · 8 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; 2 where Syntology's instrument failed) · 5 unverified (of 13 harvested samples)
• Tuning Frequency Bias in Neural Network Training with Nonuniform Data
  28 May 2022 · 0 repositories · arXiv:2205.14300
• Analyzing Tree Architectures in Ensembles via Neural Tangent Kernel
  25 May 2022 · 0 repositories · arXiv:2205.12904
• TorchNTK: A Library for Calculation of Neural Tangent Kernels of PyTorch Models
  24 May 2022 · 0 repositories · arXiv:2205.12372
• Memorization and Optimization in Deep Neural Networks with Minimum Over-parameterization
  20 May 2022 · 0 repositories · arXiv:2205.10217
• Mean-Field Analysis of Two-Layer Neural Networks: Global Optimality with Linear Convergence Rates
  19 May 2022 · 0 repositories · arXiv:2205.09860
• Self-Consistent Dynamical Field Theory of Kernel Evolution in Wide Neural Networks
  19 May 2022 · 0 repositories · arXiv:2205.09653
• On Feature Learning in Neural Networks with Global Convergence Guarantees
  22 Apr 2022 · 0 repositories · arXiv:2204.10782
• Single-level Adversarial Data Synthesis based on Neural Tangent Kernels
  8 Apr 2022 · 2 repositories · arXiv:2204.04090
• Neural Q-learning for solving PDEs
  31 Mar 2022 · 0 repositories · arXiv:2203.17128
• Demystifying the Neural Tangent Kernel from a Practical Perspective: Can it be trusted for Neural Architecture Search without training?
  28 Mar 2022 · 1 repository · arXiv:2203.14577
• On the Neural Tangent Kernel Analysis of Randomly Pruned Neural Networks
  27 Mar 2022 · 0 repositories · arXiv:2203.14328
• Neural Tangent Kernel Analysis of Deep Narrow Neural Networks
  7 Feb 2022 · 1 repository · arXiv:2202.02981
  Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
• Tight Convergence Rate Bounds for Optimization Under Power Law Spectral Conditions
  2 Feb 2022 · 0 repositories · arXiv:2202.00992
• Neural Tangent Kernel Beyond the Infinite-Width Limit: Effects of Depth and Initialization
  1 Feb 2022 · 1 repository · arXiv:2202.00553
  Syntology 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) · 2 unverified (of 3 harvested samples) · 3 pointer-only (licence)
• Implicit Bias of MSE Gradient Optimization in Underparameterized Neural Networks
  12 Jan 2022 · 0 repositories · arXiv:2201.04738
• Rethinking Influence Functions of Neural Networks in the Over-parameterized Regime
  15 Dec 2021 · 0 repositories · arXiv:2112.08297
• Understanding Square Loss in Training Overparametrized Neural Network Classifiers
  7 Dec 2021 · 0 repositories · arXiv:2112.03657
• Fast Graph Neural Tangent Kernel via Kronecker Sketching
  4 Dec 2021 · 0 repositories · arXiv:2112.02446
• A Structured Dictionary Perspective on Implicit Neural Representations
  3 Dec 2021 · 1 repository · arXiv:2112.01917
  Syntology official (archive's flag): 6 ran · 6 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; 0 where Syntology's instrument failed) · 0 unverified (of 6 harvested samples)
• Neural Tangent Kernel of Matrix Product States: Convergence and Applications
  28 Nov 2021 · 0 repositories · arXiv:2111.14046
• On the Equivalence between Neural Network and Support Vector Machine
  11 Nov 2021 · 1 repository · arXiv:2111.06063
  Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 10 harvested samples)
• New Insights into Graph Convolutional Networks using Neural Tangent Kernels
  8 Oct 2021 · 0 repositories · arXiv:2110.04060
• Neural Tangent Kernel Empowered Federated Learning
  7 Oct 2021 · 0 repositories · arXiv:2110.03681
  Syntology 0 ran · 2 unverified (of 2 harvested samples) · 2 pointer-only (licence)
• Efficient Computation of Deep Nonlinear Infinite-Width Neural Networks that Learn Features
  29 Sep 2021 · 0 repositories
• On feature learning in shallow and multi-layer neural networks with global convergence guarantees
  29 Sep 2021 · 0 repositories
• Takeuchi's Information Criteria as Generalization Measures for DNNs Close to NTK Regime
  29 Sep 2021 · 0 repositories
• The NTK Adversary: An Approach to Adversarial Attacks without any Model Access
  29 Sep 2021 · 0 repositories
• The Curse of Depth in Kernel Regime
  22 Sep 2021 · 0 repositories
• Deformed semicircle law and concentration of nonlinear random matrices for ultra-wide neural networks
  20 Sep 2021 · 0 repositories · arXiv:2109.09304
• Simple, Fast, and Flexible Framework for Matrix Completion with Infinite Width Neural Networks
  31 Jul 2021 · 1 repository · arXiv:2108.00131
• Deep Networks Provably Classify Data on Curves
  29 Jul 2021 · 0 repositories · arXiv:2107.14324
• Stability & Generalisation of Gradient Descent for Shallow Neural Networks without the Neural Tangent Kernel
  27 Jul 2021 · 0 repositories · arXiv:2107.12723
• Neural Contextual Bandits without Regret
  7 Jul 2021 · 1 repository · arXiv:2107.03144
  Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)
• Saddle-to-Saddle Dynamics in Deep Linear Networks: Small Initialization Training, Symmetry, and Sparsity
  30 Jun 2021 · 0 repositories · arXiv:2106.15933
• Understanding Dynamics of Nonlinear Representation Learning and Its Application
  28 Jun 2021 · 0 repositories · arXiv:2106.14836
• On the Convergence and Calibration of Deep Learning with Differential Privacy
  15 Jun 2021 · 1 repository · arXiv:2106.07830
• Scaling Neural Tangent Kernels via Sketching and Random Features
  15 Jun 2021 · 1 repository · arXiv:2106.07880
• What can linearized neural networks actually say about generalization?
  12 Jun 2021 · 1 repository · arXiv:2106.06770
  Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples)
• DNN-Based Topology Optimisation: Spatial Invariance and Neural Tangent Kernel
  10 Jun 2021 · 1 repository · arXiv:2106.05710
• Neural Tangent Kernel Maximum Mean Discrepancy
  6 Jun 2021 · 1 repository · arXiv:2106.03227
• Fundamental tradeoffs between memorization and robustness in random features and neural tangent regimes
  4 Jun 2021 · 1 repository · arXiv:2106.02630
• A Theory of Neural Tangent Kernel Alignment and Its Influence on Training
  29 May 2021 · 0 repositories · arXiv:2105.14301
• Properties of the After Kernel
  21 May 2021 · 0 repositories · arXiv:2105.10585
• Tensor Programs IIb: Architectural Universality of Neural Tangent Kernel Training Dynamics
  8 May 2021 · 0 repositories · arXiv:2105.03703
• One-pass Stochastic Gradient Descent in Overparametrized Two-layer Neural Networks
  1 May 2021 · 0 repositories · arXiv:2105.00262
• Unsupervised Shape Completion via Deep Prior in the Neural Tangent Kernel Perspective
  19 Apr 2021 · 0 repositories · arXiv:2104.09023
• A Recipe for Global Convergence Guarantee in Deep Neural Networks
  12 Apr 2021 · 0 repositories · arXiv:2104.05785
• How rotational invariance of common kernels prevents generalization in high dimensions
  9 Apr 2021 · 1 repository · arXiv:2104.04244
• Spectral Analysis of the Neural Tangent Kernel for Deep Residual Networks
  7 Apr 2021 · 0 repositories · arXiv:2104.03093
• Random Features for the Neural Tangent Kernel
  3 Apr 2021 · 0 repositories · arXiv:2104.01351
• Learning with Neural Tangent Kernels in Near Input Sparsity Time
  1 Apr 2021 · 0 repositories · arXiv:2104.00415
• Weighted Neural Tangent Kernel: A Generalized and Improved Network-Induced Kernel
  22 Mar 2021 · 1 repository · arXiv:2103.11558
• On the Generalization Power of Overfitted Two-Layer Neural Tangent Kernel Models
  9 Mar 2021 · 0 repositories · arXiv:2103.05243
• Meta-Learning with Neural Tangent Kernels
  7 Feb 2021 · 0 repositories · arXiv:2102.03909
• On the Proof of Global Convergence of Gradient Descent for Deep ReLU Networks with Linear Widths
  24 Jan 2021 · 0 repositories · arXiv:2101.09612
• Meta-Learning in Reproducing Kernel Hilbert Space
  1 Jan 2021 · 0 repositories
• NNGeometry: Easy and Fast Fisher Information Matrices and Neural Tangent Kernels in PyTorch
  1 Jan 2021 · 0 repositories
• Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks
  21 Dec 2020 · 0 repositories · arXiv:2012.11654
• On the eigenvector bias of Fourier feature networks: From regression to solving multi-scale PDEs with physics-informed neural networks
  18 Dec 2020 · 1 repository · arXiv:2012.10047
• Analyzing Finite Neural Networks: Can We Trust Neural Tangent Kernel Theory?
  8 Dec 2020 · 0 repositories · arXiv:2012.04477
• Feature Learning in Infinite-Width Neural Networks
  30 Nov 2020 · 4 repositories · arXiv:2011.14522
  Syntology community repositories only · 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)
• Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel
  28 Oct 2020 · 0 repositories · arXiv:2010.15110
• Beyond Lazy Training for Over-parameterized Tensor Decomposition
  22 Oct 2020 · 0 repositories · arXiv:2010.11356
• Label-Aware Neural Tangent Kernel: Toward Better Generalization and Local Elasticity
  22 Oct 2020 · 1 repository · arXiv:2010.11775
• A Theoretical Analysis of Catastrophic Forgetting through the NTK Overlap Matrix
  7 Oct 2020 · 2 repositories · arXiv:2010.04003
  Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified (of 13 harvested samples)
• Dynamically Stable Infinite-Width Limits of Neural Classifiers
  28 Sep 2020 · 0 repositories
• Predicting the Outputs of Finite Networks Trained with Noisy Gradients
  28 Sep 2020 · 0 repositories
• Kernel-Based Smoothness Analysis of Residual Networks
  21 Sep 2020 · 1 repository · arXiv:2009.10008
• Self-Adaptive Physics-Informed Neural Networks using a Soft Attention Mechanism
  7 Sep 2020 · 2 repositories · arXiv:2009.04544
• Deep Networks and the Multiple Manifold Problem
  25 Aug 2020 · 0 repositories · arXiv:2008.11245
• Finite Versus Infinite Neural Networks: an Empirical Study
  31 Jul 2020 · 0 repositories · arXiv:2007.15801
• When and why PINNs fail to train: A neural tangent kernel perspective
  28 Jul 2020 · 1 repository · arXiv:2007.14527
• Geometric compression of invariant manifolds in neural nets
  22 Jul 2020 · 1 repository · arXiv:2007.11471
  Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
• Towards an Understanding of Residual Networks Using Neural Tangent Hierarchy (NTH)
  7 Jul 2020 · 0 repositories · arXiv:2007.03714
• On the Similarity between the Laplace and Neural Tangent Kernels
  3 Jul 2020 · 1 repository · arXiv:2007.01580
  Syntology 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)
• Associative Memory in Iterated Overparameterized Sigmoid Autoencoders
  30 Jun 2020 · 0 repositories · arXiv:2006.16540
• Tensor Programs II: Neural Tangent Kernel for Any Architecture
  25 Jun 2020 · 2 repositories · arXiv:2006.14548
• The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks
  25 Jun 2020 · 0 repositories · arXiv:2006.14599
• On the Empirical Neural Tangent Kernel of Standard Finite-Width Convolutional Neural Network Architectures
  24 Jun 2020 · 0 repositories · arXiv:2006.13645
• Optimal Rates for Averaged Stochastic Gradient Descent under Neural Tangent Kernel Regime
  22 Jun 2020 · 0 repositories · arXiv:2006.12297
• Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains
  18 Jun 2020 · 17 repositories · arXiv:2006.10739
  Syntology community repositories only · 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples) · 3 pointer-only (licence)
• Collegial Ensembles
  13 Jun 2020 · 0 repositories · arXiv:2006.07678
• Dynamically Stable Infinite-Width Limits of Neural Classifiers
  11 Jun 2020 · 1 repository · arXiv:2006.06574
  Syntology official (archive's flag): 11 ran · 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 14 harvested samples)