← Keywords

neural tangent kernel

205 papers

Explore in graph

Also known as

NTK

Co-occurring keywords

neural network (6616) gradient descent (1143) kernel methods (1096) representation learning (6174) feature learning (1309) gaussian process (1198) generalization bound (649) training dynamics (113) kernel regression (86) deep learning theory (36)

Papers

NTK-approximating MLP Fusion for Efficient Language Model Fine-tuning ICML 2023
Dataset Distillation with Convexified Implicit Gradients ICML 2023
Averaged Method of Multipliers for Bi-Level Optimization without Lower-Level Strong Convexity ICML 2023
An Optimization-based Algorithm for Non-stationary Kernel Bandits without Prior Knowledge AISTATS 2023
Bounding the Width of Neural Networks via Coupled Initialization A Worst Case Analysis ICML 2022
How to Train Your Wide Neural Network Without Backprop: An Input-Weight Alignment Perspective ICML 2022
Embedded Ensembles: infinite width limit and operating regimes AISTATS 2022
NeuralEF: Deconstructing Kernels by Deep Neural Networks ICML 2022
Demystifying the Neural Tangent Kernel From a Practical Perspective: Can It Be Trusted for Neural Architecture Search Without Training? CVPR 2022
MetaNODE: Prototype Optimization as a Neural ODE for Few-Shot Learning AAAI 2022
Disentangling the Predictive Variance of Deep Ensembles through the Neural Tangent Kernel NIPS 2022
Efficient Dataset Distillation using Random Feature Approximation NIPS 2022
Identifying good directions to escape the NTK regime and efficiently learn low-degree plus sparse polynomials NIPS 2022
Memorization and Optimization in Deep Neural Networks with Minimum Over-parameterization NIPS 2022
Rethinking Influence Functions of Neural Networks in the Over-Parameterized Regime AAAI 2022
Understanding Square Loss in Training Overparametrized Neural Network Classifiers NIPS 2022
What Can the Neural Tangent Kernel Tell Us About Adversarial Robustness? NIPS 2022
Accelerated Linearized Laplace Approximation for Bayesian Deep Learning NIPS 2022
"Lossless" Compression of Deep Neural Networks: A High-dimensional Neural Tangent Kernel Approach NIPS 2022
A Neural Pre-Conditioning Active Learning Algorithm to Reduce Label Complexity NIPS 2022
Universality of empirical risk minimization COLT 2022
Transition to Linearity of General Neural Networks with Directed Acyclic Graph Architecture NIPS 2022
Generalization Properties of NAS under Activation and Skip Connection Search NIPS 2022
Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization) NIPS 2022
Exact learning dynamics of deep linear networks with prior knowledge NIPS 2022