On Interpolation Formulas Describing Neural Network Generalization

• URL: http://arxiv.org/abs/2603.13872v1
• Date: Sat, 14 Mar 2026 10:03:29 GMT
• Title: On Interpolation Formulas Describing Neural Network Generalization
• Abstract summary: 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.
• Score: 8.154667543705687
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In 2020 Domingos introduced an interpolation formula valid for "every model trained by gradient descent". He concluded that such models behave approximately as kernel machines. In this work, we extend the Domingos formula to stochastic training. We introduce a stochastic gradient kernel that extends the deterministic version via a continuous-time diffusion approximation. We prove stochastic Domingos theorems and show that the expected network output admits a kernel-machine representation with optimizer-specific weighting. It reveals that training samples contribute through loss-dependent weights and gradient alignment along the training trajectory. We then link the generalization error to the null space of the integral operator induced by the stochastic gradient kernel. The same path-kernel viewpoint provides a unified interpretation of diffusion models and GANs: diffusion induces stage-wise, noise-localized corrections, whereas GANs induce distribution-guided corrections shaped by discriminator geometry. We visualize the evolution of implicit kernels during optimization and quantify out-of-distribution behaviors through a series of numerical experiments. Our results support a feature-space memory view of learning: training stores data-dependent information in an evolving tangent feature geometry, and predictions at test time arise from kernel-weighted retrieval and aggregation of these stored features, with generalization governed by alignment between test points and the learned feature memory.

Related papers

• Generalization, memorization, and overfitting for diffusion models trained in the lazy high-dimensional regime [17.718748692214508]
  We develop a generative counterpart to the theory of benign overfitting and algorithmic regularization for neural networks.<n>We derive exact risk trajectories under gradient flow training.<n>We analyze how these estimators combine along the reverse-time SDE and characterize the distribution of the resulting samples.
  arXiv  Detail & Related papers  (2026-08-25T00:54:59Z)
• Second-Order Path Kernel Interpolation Formulas in Machine Learning [8.154667543705687]
  Pedro Domingos proposed an integral formula valid for every model learned by gradient descent.<n>In this paper, we develop second-order forms of these formulas.<n>We also establish a concentration estimate for the terminal prediction, identifying the fluctuation scale around the expected second-order representation.
  arXiv  Detail & Related papers  (2026-06-05T17:49:19Z)
• From Scores to Gibbs Correctors: Accelerating Uniform-Rate Discrete Diffusion Models [58.02657021435213]
  We propose a novel Gibbs-based corrector for discrete diffusion models, termed Gibbs-Accelerated Discrete Diffusion (GADD)<n>We show GADD achieves an overall sampling complexity of $mathcalO(mathrmpolylog (varepsilon-1)$, yielding the first such rate for diffusion-based samplers for uniform-rate discrete diffusion models.
  arXiv  Detail & Related papers  (2026-05-26T17:52:28Z)
• An Analytical Theory of Spectral Bias in the Learning Dynamics of Diffusion Models [29.972063833424215]
  We develop an analytical framework for understanding how the generated distribution evolves during diffusion model training.<n>We integrate the resulting probability-flow ODE, yielding analytic expressions for the generated distribution.
  arXiv  Detail & Related papers  (2025-03-05T05:50:38Z)
• 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 $mathcalO( ln(T) / T 1 - frac1alpha ).
  arXiv  Detail & Related papers  (2024-03-11T09:10:37Z)
• A theory of data variability in Neural Network Bayesian inference [0.70224924046445]
  We provide a field-theoretic formalism which covers the generalization properties of infinitely wide networks. We derive the generalization properties from the statistical properties of the input. We show that data variability leads to a non-Gaussian action reminiscent of a ($varphi3+varphi4$)-theory.
  arXiv  Detail & Related papers  (2023-07-31T14:11:32Z)
• Score-based Diffusion Models in Function Space [137.70916238028306]
  Diffusion models have recently emerged as a powerful framework for generative modeling.<n>This work introduces a mathematically rigorous framework called Denoising Diffusion Operators (DDOs) for training diffusion models in function space.<n>We show that the corresponding discretized algorithm generates accurate samples at a fixed cost independent of the data resolution.
  arXiv  Detail & Related papers  (2023-02-14T23:50:53Z)
• Score-based Continuous-time Discrete Diffusion Models [102.65769839899315]
  We extend diffusion models to discrete variables by introducing a Markov jump process where the reverse process denoises via a continuous-time Markov chain. We show that an unbiased estimator can be obtained via simple matching the conditional marginal distributions. We demonstrate the effectiveness of the proposed method on a set of synthetic and real-world music and image benchmarks.
  arXiv  Detail & Related papers  (2022-11-30T05:33:29Z)
• 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 Mean-Field Theory for Learning the Sch\"{o}nberg Measure of Radial Basis Functions [13.503048325896174]
  We learn the distribution in the Sch"onberg integral representation of the radial basis functions from training samples. We prove that in the scaling limits, the empirical measure of the Langevin particles converges to the law of a reflected Ito diffusion-drift process.
  arXiv  Detail & Related papers  (2020-06-23T21:04:48Z)
• SLEIPNIR: Deterministic and Provably Accurate Feature Expansion for Gaussian Process Regression with Derivatives [86.01677297601624]
  We propose a novel approach for scaling GP regression with derivatives based on quadrature Fourier features. We prove deterministic, non-asymptotic and exponentially fast decaying error bounds which apply for both the approximated kernel as well as the approximated posterior.
  arXiv  Detail & Related papers  (2020-03-05T14:33:20Z)
• Spectrum Dependent Learning Curves in Kernel Regression and Wide Neural Networks [17.188280334580195]
  We derive analytical expressions for the generalization performance of kernel regression as a function of the number of training samples. Our expressions apply to wide neural networks due to an equivalence between training them and kernel regression with the Neural Kernel Tangent (NTK) We verify our theory with simulations on synthetic data and MNIST dataset.
  arXiv  Detail & Related papers  (2020-02-07T00:03:40Z)

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.