Feature Identification via the Empirical NTK

• URL: http://arxiv.org/abs/2510.00468v2
• Date: Thu, 09 Oct 2025 17:53:08 GMT
• Title: Feature Identification via the Empirical NTK
• Authors: Jennifer Lin,
• Abstract summary: We provide evidence that eigenanalysis of the empirical neural tangent kernel (eNTK) can surface the features used by trained neural networks.<n>We find that eNTK exhibits sharp spectral cliffs whose top eigenspaces align with ground-truth features.<n>We provide evidence that a layerwise eNTK localizes features to specific layers and that the evolution of the eNTK spectrum can be used to diagnose the grokking phase transition.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We provide evidence that eigenanalysis of the empirical neural tangent kernel (eNTK) can surface the features used by trained neural networks. Across two standard toy models for mechanistic interpretability, Toy Models of Superposition (TMS) and a 1-layer MLP trained on modular addition, we find that the eNTK exhibits sharp spectral cliffs whose top eigenspaces align with ground-truth features. In TMS, the eNTK recovers the ground-truth features in both the sparse (high superposition) and dense regimes. In modular arithmetic, the eNTK can be used to recover Fourier feature families. Moreover, we provide evidence that a layerwise eNTK localizes features to specific layers and that the evolution of the eNTK spectrum can be used to diagnose the grokking phase transition. These results suggest that eNTK analysis may provide a practical handle for feature discovery and for detecting phase changes in small models.

Related papers

• The Deepfake Detective: Interpreting Neural Forensics Through Sparse Features and Manifolds [0.0]
  We present a mechanistic interpretability framework for deepfake detection applied to a vision-language model.<n>Our approach combines a sparse autoencoder analysis of internal network representations with a novel forensic manifold analysis.
  arXiv  Detail & Related papers  (2025-12-25T13:27:56Z)
• Global Convergence and Rich Feature Learning in $L$-Layer Infinite-Width Neural Networks under $μ$P Parametrization [66.03821840425539]
  In this paper, we investigate the training dynamics of $L$-layer neural networks using the tensor gradient program (SGD) framework.<n>We show that SGD enables these networks to learn linearly independent features that substantially deviate from their initial values.<n>This rich feature space captures relevant data information and ensures that any convergent point of the training process is a global minimum.
  arXiv  Detail & Related papers  (2025-03-12T17:33:13Z)
• Geometric Neural Process Fields [58.77241763774756]
  Geometric Neural Process Fields (G-NPF) is a probabilistic framework for neural radiance fields that explicitly captures uncertainty.<n>Building on these bases, we design a hierarchical latent variable model, allowing G-NPF to integrate structural information across multiple spatial levels.<n> Experiments on novel-view synthesis for 3D scenes, as well as 2D image and 1D signal regression, demonstrate the effectiveness of our method.
  arXiv  Detail & Related papers  (2025-02-04T14:17:18Z)
• Analytic Convolutional Layer: A Step to Analytic Neural Network [15.596391258983463]
  Analytic Convolutional Layer (ACL) is a mosaic of analytical convolution kernels (ACKs) and traditional convolution kernels. ACLs offer a means for neural network interpretation, thereby paving the way for the intrinsic interpretability of neural network.
  arXiv  Detail & Related papers  (2024-07-03T07:10:54Z)
• Unraveling Feature Extraction Mechanisms in Neural Networks [10.13842157577026]
  We propose a theoretical approach based on Neural Tangent Kernels (NTKs) to investigate such mechanisms. We reveal how these models leverage statistical features during gradient descent and how they are integrated into final decisions. We find that while self-attention and CNN models may exhibit limitations in learning n-grams, multiplication-based models seem to excel in this area.
  arXiv  Detail & Related papers  (2023-10-25T04:22:40Z)
• Momentum Diminishes the Effect of Spectral Bias in Physics-Informed Neural Networks [72.09574528342732]
  Physics-informed neural network (PINN) algorithms have shown promising results in solving a wide range of problems involving partial differential equations (PDEs) They often fail to converge to desirable solutions when the target function contains high-frequency features, due to a phenomenon known as spectral bias. In the present work, we exploit neural tangent kernels (NTKs) to investigate the training dynamics of PINNs evolving under gradient descent with momentum (SGDM)
  arXiv  Detail & Related papers  (2022-06-29T19:03:10Z)
• On Feature Learning in Neural Networks with Global Convergence Guarantees [49.870593940818715]
  We study the optimization of wide neural networks (NNs) via gradient flow (GF) We show that when the input dimension is no less than the size of the training set, the training loss converges to zero at a linear rate under GF. We also show empirically that, unlike in the Neural Tangent Kernel (NTK) regime, our multi-layer model exhibits feature learning and can achieve better generalization performance than its NTK counterpart.
  arXiv  Detail & Related papers  (2022-04-22T15:56:43Z)
• Exploring Linear Feature Disentanglement For Neural Networks [63.20827189693117]
  Non-linear activation functions, e.g., Sigmoid, ReLU, and Tanh, have achieved great success in neural networks (NNs) Due to the complex non-linear characteristic of samples, the objective of those activation functions is to project samples from their original feature space to a linear separable feature space. This phenomenon ignites our interest in exploring whether all features need to be transformed by all non-linear functions in current typical NNs.
  arXiv  Detail & Related papers  (2022-03-22T13:09:17Z)
• The Spectral Bias of Polynomial Neural Networks [63.27903166253743]
  Polynomial neural networks (PNNs) have been shown to be particularly effective at image generation and face recognition, where high-frequency information is critical. Previous studies have revealed that neural networks demonstrate a $textitspectral bias$ towards low-frequency functions, which yields faster learning of low-frequency components during training. Inspired by such studies, we conduct a spectral analysis of the Tangent Kernel (NTK) of PNNs. We find that the $Pi$-Net family, i.e., a recently proposed parametrization of PNNs, speeds up the
  arXiv  Detail & Related papers  (2022-02-27T23:12:43Z)
• Deep learning and high harmonic generation [0.0]
  We explore the utility of various deep neural networks (NNs) when applied to high harmonic generation (HHG) scenarios. First, we train the NNs to predict the time-dependent dipole and spectra of HHG emission from reduced-dimensionality models of di- and triatomic systems. We then demonstrate that transfer learning can be applied to our networks to expand the range of applicability of the networks.
  arXiv  Detail & Related papers  (2020-12-18T16:13:17Z)
• On the eigenvector bias of Fourier feature networks: From regression to solving multi-scale PDEs with physics-informed neural networks [0.0]
  We show that neural networks (PINNs) struggle in cases where the target functions to be approximated exhibit high-frequency or multi-scale features. We construct novel architectures that employ multi-scale random observational features and justify how such coordinate embedding layers can lead to robust and accurate PINN models.
  arXiv  Detail & Related papers  (2020-12-18T04:19:30Z)
• Scalable Partial Explainability in Neural Networks via Flexible Activation Functions [13.71739091287644]
  High dimensional features and decisions given by deep neural networks (NN) require new algorithms and methods to expose its mechanisms. Current state-of-the-art NN interpretation methods focus more on the direct relationship between NN outputs and inputs rather than the NN structure and operations itself. In this paper, we achieve partially explainable learning model by symbolically explaining the role of activation functions (AF) under a scalable topology.
  arXiv  Detail & Related papers  (2020-06-10T20:30:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.