The proton structure one mode at a time: a Neural Tangent Kernel analysis of a DIS fit
Abstract
We study the training dynamics of a feed-forward neural network (NN) through the analysis of the neural tangent kernel (NTK) in a phenomenologically relevant fit of parton distribution functions (PDFs) from deep inelastic scattering (DIS) data. The exact integration of the gradient flow derived in a previous single-flavour analysis is generalised to the multi-flavour case, yielding an analytical perspective on the relationship between data and methodology during training. The Shapley value recently used in the context of PDFs is derived within our statistical framework for observables that depend linearly on the PDFs, and we outline a geometric interpretation of training. We expose the role of gradient-based optimisation algorithms and of the parametrisation in the regularisation of the ill-posed inverse problem that affects the determination of PDFs from experimental data, demonstrating that the regularisation amounts to the incremental inclusion of NTK modes, each learned at the timescale set by the corresponding eigenvalue. We find that only a few leading modes of the NTK are necessary to reconstruct the target PDFs, while the noise of the data is carried by the sub-leading ones learned at later stages of training. Finally, we consider the impact of the initialisation on the training dynamics, and recover a transient behaviour observed in the previous analysis and in the machine learning (ML) literature. Beyond sharpening our understanding of the training dynamics, our framework can be applied to other parametrisations (such as fixed functional forms) and ML applications in physics, as well as to stress tests in the presence of inconsistent data.
Related
- Learning the Geometry of Materials Space with Trained Neural Tangent Kernels
- Well-posedness of neural turbulence closures and tangent dissipation
- Physics-informed neural networks for soliton solutions and parameter identification of the two-mode Korteweg–de Vries equation
- Probing the proton structure with minimum bias and low-pt dimuon events at hadron colliders
- From Ground State to Electronic and Vibronic Spectra via Memory Kernel Coupling Theory and Neural Quantum States
BibTeX
@misc{chiefa2026proton,
title = {{The proton structure one mode at a time: a Neural Tangent Kernel analysis of a DIS fit}},
author = {Amedeo Chiefa and Luigi Del Debbio and Richard Kenway},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.36034},
eprint = {2610.36034},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.36034},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - The proton structure one mode at a time: a Neural Tangent Kernel analysis of a DIS fit
AU - Amedeo Chiefa
AU - Luigi Del Debbio
AU - Richard Kenway
PY - 2026
DA - 2026/10/26
PB - arXiv
DO - 10.48550/arxiv.2610.36034
UR - https://arxiv.org/abs/2610.36034
AB - We study the training dynamics of a feed-forward neural network (NN) through the analysis of the neural tangent kernel (NTK) in a phenomenologically relevant fit of parton distribution functions (PDFs) from deep inelastic scattering (DIS) data. The exact integration of the gradient flow derived in a previous single-flavour analysis is generalised to the multi-flavour case, yielding an analytical perspective on the relationship between data and methodology during training. The Shapley value recently used in the context of PDFs is derived within our statistical framework for observables that depend linearly on the PDFs, and we outline a geometric interpretation of training. We expose the role of gradient-based optimisation algorithms and of the parametrisation in the regularisation of the ill-posed inverse problem that affects the determination of PDFs from experimental data, demonstrating that the regularisation amounts to the incremental inclusion of NTK modes, each learned at the timescale set by the corresponding eigenvalue. We find that only a few leading modes of the NTK are necessary to reconstruct the target PDFs, while the noise of the data is carried by the sub-leading ones learned at later stages of training. Finally, we consider the impact of the initialisation on the training dynamics, and recover a transient behaviour observed in the previous analysis and in the machine learning (ML) literature. Beyond sharpening our understanding of the training dynamics, our framework can be applied to other parametrisations (such as fixed functional forms) and ML applications in physics, as well as to stress tests in the presence of inconsistent data.
ER -