How does feature learning reshape the function space?

• URL: http://arxiv.org/abs/2605.17718v1
• Date: Mon, 18 May 2026 00:41:20 GMT
• Title: How does feature learning reshape the function space?
• Abstract summary: We study how the function space spanned by the features of a two-layer neural network evolves during gradient descent training.<n>Our results provide a precise function-space perspective on early-stage feature learning.
• Score: 17.342357780996174
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Feature learning is widely regarded as the key mechanism distinguishing neural networks from fixed-kernel methods, yet its impact on the induced function space remains poorly understood. In this work, we precisely characterize how the function space spanned by the features of a two-layer neural network evolves during gradient descent training. We prove that, in the high-dimensional proportional regime, after a large gradient step the post-update feature distribution is well approximated by a target-dependent spiked Gaussian covariance. This induces a data-adaptive kernel that reshapes the function space and modifies its spectral structure. Our analysis reveals that feature learning can be interpreted as a distributional transformation in either parameter space or input space, equivalently as the introduction of a target-dependent kernel. In particular, it selectively amplifies eigenvalues aligned with the target direction and mixes leading eigenfunctions, coupling the top radial mode with a target-aligned quadratic harmonic. Overall, our results provide a precise function-space perspective on early-stage feature learning: rather than just rescaling a fixed kernel, gradient descent induces a data-adaptive deformation that preferentially enhances directions aligned with the signal in the data.

Related papers

• On Interpolation Formulas Describing Neural Network Generalization [8.154667543705687]
  We introduce a gradient kernel that extends the deterministic version via a continuous-time diffusion.<n>It reveals that training samples contribute through loss-dependent weights and gradient alignment along the trajectory.<n>We visualize then link the generalization error to the null space of the integral operator induced by the gradient kernel.
  arXiv  Detail & Related papers  (2026-03-14T10:03:29Z)
• Function Spaces Without Kernels: Learning Compact Hilbert Space Representations [17.20282687120807]
  We show that function encoders provide a principled connection to feature learning and kernel methods.<n>We develop two training algorithms that learn compact bases.<n>This work suggests a path toward neural predictors with kernel-level guarantees.
  arXiv  Detail & Related papers  (2025-09-24T22:55:52Z)
• Diagonal Over-parameterization in Reproducing Kernel Hilbert Spaces as an Adaptive Feature Model: Generalization and Adaptivity [11.644182973599788]
  diagonal adaptive kernel model learns kernel eigenvalues and output coefficients simultaneously during training.<n>We show that the adaptivity comes from learning the right eigenvalues during training.
  arXiv  Detail & Related papers  (2025-01-15T09:20:02Z)
• A Random Matrix Theory Perspective on the Spectrum of Learned Features and Asymptotic Generalization Capabilities [30.737171081270322]
  We study how fully-connected two-layer neural networks adapt to the target function after a single, but aggressive, gradient descent step. This provides a sharp description of the impact of feature learning in the generalization of two-layer neural networks, beyond the random features and lazy training regimes.
  arXiv  Detail & Related papers  (2024-10-24T17:24:34Z)
• Adaptive Federated Learning Over the Air [108.62635460744109]
  We propose a federated version of adaptive gradient methods, particularly AdaGrad and Adam, within the framework of over-the-air model training. Our analysis shows that the AdaGrad-based training algorithm converges to a stationary point at the rate of $mathcalO( ln(T) / T 1 - frac1alpha ).
  arXiv  Detail & Related papers  (2024-03-11T09:10:37Z)
• Nonlinear functional regression by functional deep neural network with kernel embedding [18.927592350748682]
  We introduce a functional deep neural network with an adaptive and discretization-invariant dimension reduction method.<n>Explicit rates of approximating nonlinear smooth functionals across various input function spaces are derived.<n>We conduct numerical experiments on both simulated and real datasets to demonstrate the effectiveness and benefits of our functional net.
  arXiv  Detail & Related papers  (2024-01-05T16:43:39Z)
• Gradient-Based Feature Learning under Structured Data [57.76552698981579]
  In the anisotropic setting, the commonly used spherical gradient dynamics may fail to recover the true direction. We show that appropriate weight normalization that is reminiscent of batch normalization can alleviate this issue. In particular, under the spiked model with a suitably large spike, the sample complexity of gradient-based training can be made independent of the information exponent.
  arXiv  Detail & Related papers  (2023-09-07T16:55:50Z)
• Promises and Pitfalls of the Linearized Laplace in Bayesian Optimization [73.80101701431103]
  The linearized-Laplace approximation (LLA) has been shown to be effective and efficient in constructing Bayesian neural networks. We study the usefulness of the LLA in Bayesian optimization and highlight its strong performance and flexibility.
  arXiv  Detail & Related papers  (2023-04-17T14:23:43Z)
• On the Benefits of Large Learning Rates for Kernel Methods [110.03020563291788]
  We show that a phenomenon can be precisely characterized in the context of kernel methods. We consider the minimization of a quadratic objective in a separable Hilbert space, and show that with early stopping, the choice of learning rate influences the spectral decomposition of the obtained solution.
  arXiv  Detail & Related papers  (2022-02-28T13:01:04Z)
• A Functional Perspective on Learning Symmetric Functions with Neural Networks [48.80300074254758]
  We study the learning and representation of neural networks defined on measures. We establish approximation and generalization bounds under different choices of regularization. The resulting models can be learned efficiently and enjoy generalization guarantees that extend across input sizes.
  arXiv  Detail & Related papers  (2020-08-16T16:34:33Z)
• Can Temporal-Difference and Q-Learning Learn Representation? A Mean-Field Theory [110.99247009159726]
  Temporal-difference and Q-learning play a key role in deep reinforcement learning, where they are empowered by expressive nonlinear function approximators such as neural networks. In particular, temporal-difference learning converges when the function approximator is linear in a feature representation, which is fixed throughout learning, and possibly diverges otherwise.
  arXiv  Detail & Related papers  (2020-06-08T17:25:22Z)

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.