Neural Tangent Kernel Papers

This list contains papers that adopt Neural Tangent Kernel (NTK) as a main theme or core idea.
NOTE: If there are any papers I've missed, please feel free to raise an issue.

2024

Title	Venue	PDF	CODE
Faithful and Efficient Explanations for Neural Networks via Neural Tangent Kernel Surrogate Models	ICLR	PDF	CODE
PINNACLE: PINN Adaptive ColLocation and Experimental points selection	ICLR	PDF	-
On the Foundations of Shortcut Learning	ICLR	PDF	-
Understanding Reconstruction Attacks with the Neural Tangent Kernel and Dataset Distillation	ICLR	PDF	-
Sample Relationship from Learning Dynamics Matters for Generalisation	ICLR	PDF	-
Robust NAS benchmark under adversarial training: assessment, theory, and beyond	ICLR	PDF	-
Theoretical Analysis of Robust Overfitting for Wide DNNs: An NTK Approach	ICLR	PDF	CODE
Heterogeneous Personalized Federated Learning by Local-Global Updates Mixing via Convergence Rate	ICLR	PDF	-
Neural Network-Based Score Estimation in Diffusion Models: Optimization and Generalization	ICLR	PDF	-
Grokking as the Transition from Lazy to Rich Training Dynamics	ICLR	PDF	-
Generalization of Deep ResNets in the Mean-Field Regime	ICLR	PDF	-

2023

Title	Venue	PDF	CODE
Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models	NeurIPS	PDF	CODE
Deep Learning with Kernels through RKHM and the Perron–Frobenius Operator	NeurIPS	PDF	-
A Theoretical Analysis of the Test Error of Finite-Rank Kernel Ridge Regression	NeurIPS	PDF	-
Fixing the NTK: From Neural Network Linearizations to Exact Convex Programs	NeurIPS	PDF	-
Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time	NeurIPS	PDF	-
Feature-Learning Networks Are Consistent Across Widths At Realistic Scales	NeurIPS	PDF	-
Dynamics of Finite Width Kernel and Prediction Fluctuations in Mean Field Neural Networks	NeurIPS	PDF	CODE
Spectral Evolution and Invariance in Linear-width Neural Networks	NeurIPS	PDF	-
Analyzing Generalization of Neural Networks through Loss Path Kernels	NeurIPS	PDF	-
Neural (Tangent Kernel) Collapse	NeurIPS	PDF	-
Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension	NeurIPS	PDF	CODE
A PAC-Bayesian Perspective on the Interpolating Information Criterion	NeurIPS-W	PDF	-
A Kernel Perspective of Skip Connections in Convolutional Networks	ICLR	PDF	-
Scale-invariant Bayesian Neural Networks with Connectivity Tangent Kernel	ICLR	PDF	-
Symmetric Pruning in Quantum Neural Networks	ICLR	PDF	-
The Influence of Learning Rule on Representation Dynamics in Wide Neural Networks	ICLR	PDF	-
Few-shot Backdoor Attacks via Neural Tangent Kernels	ICLR	PDF	-
Analyzing Tree Architectures in Ensembles via Neural Tangent Kernel	ICLR	PDF	-
Supervision Complexity and its Role in Knowledge Distillation	ICLR	PDF	-
NTK-SAP: Improving Neural Network Pruning By Aligning Training Dynamics	ICLR	PDF	CODE
Tuning Frequency Bias in Neural Network Training with Nonuniform Data	ICLR	PDF	-
Simple initialization and parametrization of sinusoidal networks via their kernel bandwidth	ICLR	PDF	-
Characterizing the spectrum of the NTK via a power series expansion	ICLR	PDF	CODE
Adaptive Optimization in the $\infty$-Width Limit	ICLR	PDF	-
Understanding the Generalization of Adam in Learning Neural Networks with Proper Regularization	ICLR	PDF	-
The Onset of Variance-Limited Behavior for Networks in the Lazy and Rich Regimes	ICLR	PDF	-
Restricted Strong Convexity of Deep Learning Models with Smooth Activations	ICLR	PDF	-
Feature selection and low test error in shallow low-rotation ReLU networks	ICLR	PDF	-
Exploring Active 3D Object Detection from a Generalization Perspective	ICLR	PDF	CODE
On the Neural Tangent Kernel Analysis of Randomly Pruned Neural Networks	AISTATS	PDF	-
Adversarial Noises Are Linearly Separable for (Nearly) Random Neural Networks	AISTATS	PDF	-
Regularize Implicit Neural Representation by Itself	CVPR	PDF	-
WIRE: Wavelet Implicit Neural Representations	CVPR	PDF	CODE
Regularizing Second-Order Influences for Continual Learning	CVPR	PDF	CODE
Multiplicative Fourier Level of Detail	CVPR	PDF	-
KECOR: Kernel Coding Rate Maximization for Active 3D Object Detection	ICCV	PDF	CODE
TKIL: Tangent Kernel Approach for Class Balanced Incremental Learning	ICCV-W	PDF	-
A Fast, Well-Founded Approximation to the Empirical Neural Tangent Kernel	ICML	PDF	-
Stochastic Marginal Likelihood Gradients using Neural Tangent Kernels	ICML	PDF	CODE
Graph Neural Tangent Kernel: Convergence on Large Graphs	ICML	PDF	-
Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent Kernels	ICML	PDF	CODE
Analyzing Convergence in Quantum Neural Networks: Deviations from Neural Tangent Kernels	ICML	PDF	-
Benign Overfitting in Deep Neural Networks under Lazy Training	ICML	PDF	-
Gradient Descent in Neural Networks as Sequential Learning in Reproducing Kernel Banach Space	ICML	PDF	-
A Kernel-Based View of Language Model Fine-Tuning	ICML	PDF	-
Combinatorial Neural Bandits	ICML	PDF	-
What Can Be Learnt With Wide Convolutional Neural Networks?	ICML	PDF	CODE
Reward-Biased Maximum Likelihood Estimation for Neural Contextual Bandits	AAAI	PDF	-
Neural tangent kernel at initialization: linear width suffices	UAI	PDF	-
Kernel Ridge Regression-Based Graph Dataset Distillation	SIGKDD	PDF	CODE
Analyzing Deep PAC-Bayesian Learning with Neural Tangent Kernel: Convergence, Analytic Generalization Bound, and Efficient Hyperparameter Selection	TMLR	PDF	-
The Eigenlearning Framework: A Conservation Law Perspective on Kernel Regression and Wide Neural Networks	TMLR	PDF	CODE
Empirical Limitations of the NTK for Understanding Scaling Laws in Deep Learning	TMLR	PDF	-
Analysis of Convolutions, Non-linearity and Depth in Graph Neural Networks using Neural Tangent Kernel	TMLR	PDF	-
A Framework and Benchmark for Deep Batch Active Learning for Regression	JMLR	PDF	CODE
A Continual Learning Algorithm Based on Orthogonal Gradient Descent Beyond Neural Tangent Kernel Regime	IEEE	PDF	-
The Quantum Path Kernel: A Generalized Neural Tangent Kernel for Deep Quantum Machine Learning	QE	PDF	-
NeuralBO: A Black-box Optimization Algorithm using Deep Neural Networks	NC	PDF	-
Deep Learning in Random Neural Fields: Numerical Experiments via Neural Tangent Kernel	NN	PDF	CODE
Physics-informed radial basis network (PIRBN): A local approximating neural network for solving nonlinear partial differential equations	CMAME	PDF	-
A non-gradient method for solving elliptic partial differential equations with deep neural networks	JoCP	PDF	-
Self-Adaptive Physics-Informed Neural Networks using a Soft Attention Mechanism	JoCP	PDF	-
Towards a phenomenological understanding of neural networks: data	MLST	PDF	-
Weighted Neural Tangent Kernel: A Generalized and Improved Network-Induced Kernel	ML	PDF	CODE
Tensor Programs IVb: Adaptive Optimization in the ∞-Width Limit	arXiv	PDF	-

2022

Title	Venue	PDF	CODE
Generalization Properties of NAS under Activation and Skip Connection Search	NeurIPS	PDF	-
Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study	NeurIPS	PDF	CODE
Graph Neural Network Bandits	NeurIPS	PDF	-
Lossless Compression of Deep Neural Networks: A High-dimensional Neural Tangent Kernel Approach	NeurIPS	PDF	-
GraphQNTK: Quantum Neural Tangent Kernel for Graph Data	NeurIPS	PDF	CODE
Evolution of Neural Tangent Kernels under Benign and Adversarial Training	NeurIPS	PDF	CODE
TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels	NeurIPS	PDF	CODE
Making Look-Ahead Active Learning Strategies Feasible with Neural Tangent Kernels	NeurIPS	PDF	CODE
Disentangling the Predictive Variance of Deep Ensembles through the Neural Tangent Kernel	NeurIPS	PDF	CODE
On the Generalization Power of the Overfitted Three-Layer Neural Tangent Kernel Model	NeurIPS	PDF	-
What Can the Neural Tangent Kernel Tell Us About Adversarial Robustness?	NeurIPS	PDF	-
On the Spectral Bias of Convolutional Neural Tangent and Gaussian Process Kernels	NeurIPS	PDF	-
Fast Neural Kernel Embeddings for General Activations	NeurIPS	PDF	CODE
Bidirectional Learning for Offline Infinite-width Model-based Optimization	NeurIPS	PDF	-
Infinite Recommendation Networks: A Data-Centric Approach	NeurIPS	PDF	CODE1 CODE2
Distribution-Informed Neural Networks for Domain Adaptation Regression	NeurIPS	PDF	-
Self-Consistent Dynamical Field Theory of Kernel Evolution in Wide Neural Networks	NeurIPS	PDF	-
Spectral Bias Outside the Training Set for Deep Networks in the Kernel Regime	NeurIPS	PDF	CODE
Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization)	NeurIPS	PDF	-
Transition to Linearity of General Neural Networks with Directed Acyclic Graph Architecture	NeurIPS	PDF	-
A Neural Pre-Conditioning Active Learning Algorithm to Reduce Label Complexity	NeurIPS	PDF	-
NFT-K: Non-Fungible Tangent Kernels	ICASSP	PDF	CODE
Label Propagation Across Grapsh: Node Classification Using Graph Neural Tangent Kenrels	ICASSP	PDF	-
A Neural Tangent Kernel Perspective of Infinite Tree Ensembles	ICLR	PDF	-
Neural Networks as Kernel Learners: The Silent Alignment Effect	ICLR	PDF	-
Towards Deepening Graph Neural Networks: A GNTK-based Optimization Perspective	ICLR	PDF	-
Overcoming The Spectral Bias of Neural Value Approximation	ICLR	PDF	CODE
Efficient Computation of Deep Nonlinear Infinite-Width Neural Networks that Learn Features	ICLR	PDF	CODE
Learning Neural Contextual Bandits Through Perturbed Rewards	ICLR	PDF	-
Learning Curves for Continual Learning in Neural Networks: Self-knowledge Transfer and Forgetting	ICLR	PDF	-
The Spectral Bias of Polynomial Neural Networks	ICLR	PDF	-
On Feature Learning in Neural Networks with Global Convergence Guarantees	ICLR	PDF	-
Implicit Bias of MSE Gradient Optimization in Underparameterized Neural Networks	ICLR	PDF	-
Eigenspace Restructuring: A Principle of Space and Frequency in Neural Networks	COLT	PDF	-
Neural Networks can Learn Representations with Gradient Descent	COLT	PDF	-
Neural Contextual Bandits without Regret	AISTATS	PDF	-
Finding Dynamics Preserving Adversarial Winning Tickets	AISTATS	PDF	-
Embedded Ensembles: Infinite Width Limit and Operating Regimes	AISTATS	PDF	-
Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning	CVPR	PDF	CODE
Demystifying the Neural Tangent Kernel from a Practical Perspective: Can it be trusted for Neural Architecture Search without training?	CVPR	PDF	CODE
A Structured Dictionary Perspective on Implicit Neural Representations	CVPR	PDF	CODE
NL-FFC: Non-Local Fast Fourier Convolution for Image Super Resolution	CVPR-W	PDF	CODE
Intrinsic Neural Fields: Learning Functions on Manifolds	ECCV	PDF	-
Random Gegenbauer Features for Scalable Kernel Methods	ICML	PDF	-
Fast Finite Width Neural Tangent Kernel	ICML	PDF	CODE
A Neural Tangent Kernel Perspective of GANs	ICML	PDF	CODE
Neural Tangent Kernel Empowered Federated Learning	ICML	PDF	-
Reverse Engineering the Neural Tangent Kernel	ICML	PDF	CODE
How to Train Your Wide Neural Network Without Backprop: An Input-Weight Alignment Perspective	ICML	PDF	CODE
Bounding the Width of Neural Networks via Coupled Initialization – A Worst Case Analysis –	ICML	PDF	-
Leverage Score Sampling for Tensor Product Matrices in Input Sparsity Time	ICML	PDF	-
Lazy Estimation of Variable Importance for Large Neural Networks	ICML	PDF	-
DAVINZ: Data Valuation using Deep Neural Networks at Initialization	ICML	PDF	-
Neural Tangent Kernel Beyond the Infinite-Width Limit: Effects of Depth and Initialization	ICML	PDF	CODE
NeuralEF: Deconstructing Kernels by Deep Neural Networks	ICML	PDF	CODE
Feature Learning and Signal Propagation in Deep Neural Networks	ICML	PDF	-
More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations Generalize	ICML	PDF	CODE
Fast Graph Neural Tangent Kernel via Kronecker Sketching	AAAI	PDF	-
Rethinking Influence Functions of Neural Networks in the Over-parameterized Regime	AAAI	PDF	-
On the Empirical Neural Tangent Kernel of Standard Finite-Width Convolutional Neural Network Architectures	UAI	PDF	-
Feature Learning and Random Features in Standard Finite-Width Convolutional Neural Networks: An Empirical Study	UAI	PDF	-
Out of Distribution Detection via Neural Network Anchoring	ACML	PDF	CODE
Learning Neural Ranking Models Online from Implicit User Feedback	WWW	PDF	-
Trust Your Robots! Predictive Uncertainty Estimation of Neural Networks with Sparse Gaussian Processes	CoRL	PDF	-
When and why PINNs fail to train: A neural tangent kernel perspective	CP	PDF	CODE
How Neural Architectures Affect Deep Learning for Communication Networks?	ICC	PDF	-
Loss landscapes and optimization in over-parameterized non-linear systems and neural networks	ACHA	PDF	-
Feature Purification: How Adversarial Training Performs Robust Deep Learning	FOCS	PDF	-
Kernel-Based Smoothness Analysis of Residual Networks	MSML	PDF	-
Analyzing Finite Neural Networks: Can We Trust Neural Tangent Kernel Theory?	MSML	PDF	-
The Training Response Law Explains How Deep Neural Networks Learn	IoP	PDF	-
Simple, Fast, and Flexible Framework for Matrix Completion with Infinite Width Neural Networks	PNAS	PDF	CODE
Representation Learning via Quantum Neural Tangent Kernels	PRX Quantum	PDF	-
TorchNTK: A Library for Calculation of Neural Tangent Kernels of PyTorch Models	arXiv	PDF	CODE
Neural Tangent Kernel Analysis of Shallow α-Stable ReLU Neural Networks	arXiv	PDF	-
Neural Tangent Kernel: A Survey	arXiv	PDF	-

2021

Title	Venue	PDF	CODE
Neural Tangent Kernel Maximum Mean Discrepancy	NeurIPS	PDF	-
DNN-based Topology Optimisation: Spatial Invariance and Neural Tangent Kernel	NeurIPS	PDF	-
Stability & Generalisation of Gradient Descent for Shallow Neural Networks without the Neural Tangent Kernel	NeurIPS	PDF	-
Scaling Neural Tangent Kernels via Sketching and Random Features	NeurIPS	PDF	-
Dataset Distillation with Infinitely Wide Convolutional Networks	NeurIPS	PDF	-
On the Equivalence between Neural Network and Support Vector Machine	NeurIPS	PDF	CODE
Local Signal Adaptivity: Provable Feature Learning in Neural Networks Beyond Kernels	NeurIPS	PDF	CODE
Explicit Loss Asymptotics in the Gradient Descent Training of Neural Networks	NeurIPS	PDF	-
Kernelized Heterogeneous Risk Minimization	NeurIPS	PDF	CODE
An Empirical Study of Neural Kernel Bandits	NeurIPS-W	PDF	-
The Curse of Depth in Kernel Regime	NeurIPS-W	PDF	-
Wearing a MASK: Compressed Representations of Variable-Length Sequences Using Recurrent Neural Tangent Kernels	ICASSP	PDF	CODE
The Dynamics of Gradient Descent for Overparametrized Neural Networks	L4DC	PDF	-
The Recurrent Neural Tangent Kernel	ICLR	PDF	-
Deep Neural Tangent Kernel and Laplace Kernel Have the Same RKHS	ICLR	PDF	-
Optimal Rates for Averaged Stochastic Gradient Descent under Neural Tangent Kernel Regime	ICLR	PDF	-
Meta-Learning with Neural Tangent Kernels	ICLR	PDF	-
How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks	ICLR	PDF	-
Deep Networks and the Multiple Manifold Problem	ICLR	PDF	-
Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective	ICLR	PDF	CODE
Neural Thompson Sampling	ICLR	PDF	-
Deep Equals Shallow for ReLU Networks in Kernel Regimes	ICLR	PDF	-
A Recipe for Global Convergence Guarantee in Deep Neural Networks	AAAI	PDF	-
A Deep Conditioning Treatment of Neural Networks	ALT	PDF	-
Nonparametric Regression with Shallow Overparameterized Neural Networks Trained by GD with Early Stopping	COLT	PDF	-
Learning with invariances in random features and kernel models	COLT	PDF	-
Implicit Regularization via Neural Feature Alignment	AISTATS	PDF	CODE
Regularization Matters: A Nonparametric Perspective on Overparametrized Neural Network	AISTATS	PDF	-
One-pass Stochastic Gradient Descent in Overparametrized Two-layer Neural Networks	AISTATS	PDF	-
Fast Adaptation with Linearized Neural Networks	AISTATS	PDF	CODE
Fast Learning in Reproducing Kernel Kreın Spaces via Signed Measures	AISTATS	PDF	-
Stable ResNet	AISTATS	PDF	-
A Dynamical View on Optimization Algorithms of Overparameterized Neural Networks	AISTATS	PDF	-
Can We Characterize Tasks Without Labels or Features?	CVPR	PDF	CODE
The Neural Tangent Link Between CNN Denoisers and Non-Local Filters	CVPR	PDF	CODE
Nerfies: Deformable Neural Radiance Fields	ICCV	PDF	CODE
Kernel Methods in Hyperbolic Spaces	ICCV	PDF	-
Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks	ICML	PDF	-
On the Generalization Power of Overfitted Two-Layer Neural Tangent Kernel Models	ICML	PDF	-
Tensor Programs IIb: Architectural Universality of Neural Tangent Kernel Training Dynamics	ICML	PDF	-
Tensor Programs IV: Feature Learning in Infinite-Width Neural Networks	ICML	PDF	CODE
FL-NTK: A Neural Tangent Kernel-based Framework for Federated Learning Convergence Analysis	ICML	PDF	-
On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent	ICML	PDF	-
Feature Learning in Infinite-Width Neural Networks	ICML	PDF	CODE
On Monotonic Linear Interpolation of Neural Network Parameters	ICML	PDF	-
Uniform Convergence, Adversarial Spheres and a Simple Remedy	ICML	PDF	-
Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels	ICML	PDF	-
Efficient Statistical Tests: A Neural Tangent Kernel Approach	ICML	PDF	-
Neural Tangent Generalization Attacks	ICML	PDF	CODE
On the Random Conjugate Kernel and Neural Tangent Kernel	ICML	PDF	-
Generalization Guarantees for Neural Architecture Search with Train-Validation Split	ICML	PDF	-
Tilting the playing field: Dynamical loss functions for machine learning	ICML	PDF	CODE
PHEW : Constructing Sparse Networks that Learn Fast and Generalize Well Without Training Data	ICML	PDF	-
On the Neural Tangent Kernel of Deep Networks with Orthogonal Initialization	IJCAI	PDF	CODE
Towards Understanding the Spectral Bias of Deep Learning	IJCAI	PDF	-
On Random Kernels of Residual Architectures	UAI	PDF	-
How Shrinking Gradient Noise Helps the Performance of Neural Networks	ICBD	PDF	-
Unsupervised Shape Completion via Deep Prior in the Neural Tangent Kernel Perspective	ACM TOG	PDF	-
Benefits of Jointly Training Autoencoders: An Improved Neural Tangent Kernel Analysis	TIT	PDF	-
Reinforcement Learning via Gaussian Processes with Neural Network Dual Kernels	CoG	PDF	-
Kernel-Based Smoothness Analysis of Residual Networks	MSML	PDF	-
Mathematical Models of Overparameterized Neural Networks	IEEE	PDF	-
A Feature Fusion Based Indicator for Training-Free Neural Architecture Search	IEEE	PDF	-
Pathological spectra of the Fisher information metric and its variants in deep neural networks	NC	PDF	-
Linearized two-layers neural networks in high dimension	Ann. Statist.	PDF	-
Geometric compression of invariant manifolds in neural nets	J. Stat. Mech.	PDF	CODE
A Convergence Theory Towards Practical Over-parameterized Deep Neural Networks	arXiv	PDF	-
Learning with Neural Tangent Kernels in Near Input Sparsity Time	arXiv	PDF	-
Spectral Analysis of the Neural Tangent Kernel for Deep Residual Networks	arXiv	PDF	-
Properties of the After Kernel	arXiv	PDF	CODE

2020

Title	Venue	PDF	CODE
Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations	ECCV	PDF	-
Why Do Deep Residual Networks Generalize Better than Deep Feedforward Networks? — A Neural Tangent Kernel Perspective	NeurIPS	PDF	-
Label-Aware Neural Tangent Kernel: Toward Better Generalization and Local Elasticity	NeurIPS	PDF	CODE
Finite Versus Infinite Neural Networks: an Empirical Study	NeurIPS	PDF	-
On the linearity of large non-linear models: when and why the tangent kernel is constant	NeurIPS	PDF	-
On the Similarity between the Laplace and Neural Tangent Kernels	NeurIPS	PDF	-
A Generalized Neural Tangent Kernel Analysis for Two-layer Neural Networks	NeurIPS	PDF	-
Generalization bound of globally optimal non-convex neural network training: Transportation map estimation by infinite dimensional Langevin dynamics	NeurIPS	PDF	-
Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains	NeurIPS	PDF	CODE
Network size and weights size for memorization with two-layers neural networks	NeurIPS	PDF	-
Neural Networks Learning and Memorization with (almost) no Over-Parameterization	NeurIPS	PDF	-
Towards Understanding Hierarchical Learning: Benefits of Neural Representations	NeurIPS	PDF	-
Knowledge Distillation in Wide Neural Networks: Risk Bound, Data Efficiency and Imperfect Teacher	NeurIPS	PDF	-
On Infinite-Width Hypernetworks	NeurIPS	PDF	-
Predicting Training Time Without Training	NeurIPS	PDF	-
Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel	NeurIPS	PDF	-
Spectra of the Conjugate Kernel and Neural Tangent Kernel for Linear-Width Neural Networks	NeurIPS	PDF	-
Kernel and Rich Regimes in Overparametrized Models	COLT	PDF	-
Learning Over-Parametrized Two-Layer ReLU Neural Networks beyond NTK	COLT	PDF	-
Finite Depth and Width Corrections to the Neural Tangent Kernel	ICLR	PDF	-
Neural tangent kernels, transportation mappings, and universal approximation	ICLR	PDF	-
Neural Tangents: Fast and Easy Infinite Neural Networks in Python	ICLR	PDF	CODE
Picking Winning Tickets Before Training by Preserving Gradient Flow	ICLR	PDF	CODE
Truth or Backpropaganda? An Empirical Investigation of Deep Learning Theory	ICLR	PDF	-
Simple and Effective Regularization Methods for Training on Noisily Labeled Data with Generalization Guarantee	ICLR	PDF	-
The asymptotic spectrum of the Hessian of DNN throughout training	ICLR	PDF	-
Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks	ICLR	PDF	CODE
Beyond Linearization: On Quadratic and Higher-Order Approximation of Wide Neural Networks	ICLR	PDF	-
Asymptotics of Wide Networks from Feynman Diagrams	ICLR	PDF	-
The equivalence between Stein variational gradient descent and black-box variational inference	ICLR-W	PDF	-
Neural Kernels Without Tangents	ICML	PDF	CODE
The Neural Tangent Kernel in High Dimensions: Triple Descent and a Multi-Scale Theory of Generalization	ICML	PDF	-
Dynamics of Deep Neural Networks and Neural Tangent Hierarchy	ICML	PDF	-
Disentangling Trainability and Generalization in Deep Neural Networks	ICML	PDF	-
Spectrum Dependent Learning Curves in Kernel Regression and Wide Neural Networks	ICML	PDF	CODE
Finding trainable sparse networks through Neural Tangent Transfer	ICML	PDF	CODE
Associative Memory in Iterated Overparameterized Sigmoid Autoencoders	ICML	PDF	-
Neural Contextual Bandits with UCB-based Exploration	ICML	PDF	-
Optimization Theory for ReLU Neural Networks Trained with Normalization Layers	ICML	PDF	-
Towards a General Theory of Infinite-Width Limits of Neural Classifiers	ICML	PDF	-
Generalisation guarantees for continual learning with orthogonal gradient descent	ICML-W	PDF	CODE
Neural Spectrum Alignment: Empirical Study	ICANN	PDF	-
A type of generalization error induced by initialization in deep neural networks	MSML	PDF	-
Disentangling feature and lazy training in deep neural networks	J. Stat. Mech.	PDF	CODE
Scaling description of generalization with number of parameters in deep learning	J. Stat. Mech.	PDF	CODE
Any Target Function Exists in a Neighborhood of Any Sufficiently Wide Random Network: A Geometrical Perspective	NC	PDF	-
Kolmogorov Width Decay and Poor Approximation in Machine Learning: Shallow Neural Networks, Random Feature Models and Neural Tangent Kernels	RMS	PDF	-
On the infinite width limit of neural networks with a standard parameterization	arXiv	PDF	CODE
On the Empirical Neural Tangent Kernel of Standard Finite-Width Convolutional Neural Network Architectures	arXiv	PDF	-
Infinite-Width Neural Networks for Any Architecture: Reference Implementations	arXiv	PDF	CODE
Every Model Learned by Gradient Descent Is Approximately a Kernel Machine	arXiv	PDF	-
Analyzing Finite Neural Networks: Can We Trust Neural Tangent Kernel Theory?	arXiv	PDF	-
Scalable Neural Tangent Kernel of Recurrent Architectures	arXiv	PDF	CODE
Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning	arXiv	PDF	-

2019

Title	Venue	PDF	CODE
Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernel	NeurIPS	PDF	-
Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent	NeurIPS	PDF	CODE
On Exact Computation with an Infinitely Wide Neural Net	NeurIPS	PDF	CODE
Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels	NeurIPS	PDF	CODE
On the Inductive Bias of Neural Tangent Kernels	NeurIPS	PDF	CODE
Convergence of Adversarial Training in Overparametrized Neural Networks	NeurIPS	PDF	-
Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks	NeurIPS	PDF	-
Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers	NeurIPS	PDF	-
Limitations of Lazy Training of Two-layers Neural Networks	NeurIPS	PDF	-
The Convergence Rate of Neural Networks for Learned Functions of Different Frequencies	NeurIPS	PDF	CODE
On Lazy Training in Differentiable Programming	NeurIPS	PDF	-
Information in Infinite Ensembles of Infinitely-Wide Neural Networks	AABI	PDF	-
Scaling Limits of Wide Neural Networks with Weight Sharing: Gaussian Process Behavior, Gradient Independence, and Neural Tangent Kernel Derivation	arXiv	PDF	-
Gradient Descent can Learn Less Over-parameterized Two-layer Neural Networks on Classification Problems	arXiv	PDF	-
Gram-Gauss-Newton Method: Learning Overparameterized Neural Networks for Regression Problems	arXiv	PDF	-
Mean-field Behaviour of Neural Tangent Kernel for Deep Neural Networks	arXiv	PDF	-
Order and Chaos: NTK views on DNN Normalization, Checkerboard and Boundary Artifacts	arXiv	PDF	-
A Fine-Grained Spectral Perspective on Neural Networks	arXiv	PDF	CODE
Enhanced Convolutional Neural Tangent Kernels	arXiv	PDF	-

2018

Title	Venue	PDF	CODE
Neural Tangent Kernel: Convergence and Generalization in Neural Networks	NeurIPS	PDF	-