← 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

A Framework and Benchmark for Deep Batch Active Learning for Regression JMLR 2023
Combinatorial Neural Bandits ICML 2023
Provably and Practically Efficient Neural Contextual Bandits ICML 2023
Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models NIPS 2023
Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL NIPS 2023
Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent Kernels ICML 2023
Understanding Multi-phase Optimization Dynamics and Rich Nonlinear Behaviors of ReLU Networks NIPS 2023
Provable Guarantees for Neural Networks via Gradient Feature Learning NIPS 2023
Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension NIPS 2023
Efficient Uncertainty Quantification and Reduction for Over-Parameterized Neural Networks NIPS 2023
A Theory of Unsupervised Speech Recognition ACL 2023
Second-order regression models exhibit progressive sharpening to the edge of stability ICML 2023
Unraveling Feature Extraction Mechanisms in Neural Networks EMNLP 2023
Bidirectional Learning for Offline Model-based Biological Sequence Design ICML 2023
Fixing the NTK: From Neural Network Linearizations to Exact Convex Programs NIPS 2023
Nonlinear Advantage: Trained Networks Might Not Be As Complex as You Think ICML 2023
On the Asymptotic Learning Curves of Kernel Ridge Regression under Power-law Decay NIPS 2023
Neural Q-learning for solving PDEs JMLR 2023
Spectral Evolution and Invariance in Linear-width Neural Networks NIPS 2023
A Kernel-Based View of Language Model Fine-Tuning ICML 2023
Analyzing Convergence in Quantum Neural Networks: Deviations from Neural Tangent Kernels ICML 2023
A Fast, Well-Founded Approximation to the Empirical Neural Tangent Kernel ICML 2023
On the Dynamics Under the Unhinged Loss and Beyond JMLR 2023
NTK-approximating MLP Fusion for Efficient Language Model Fine-tuning ICML 2023
Dataset Distillation with Convexified Implicit Gradients ICML 2023