English
Related papers

Related papers: Neural signature kernels as infinite-width-depth-l…

200 papers

Signature kernels have emerged as a powerful tool within kernel methods for sequential data. In the paper "The Signature Kernel is the solution of a Goursat PDE", the authors identify a kernel trick that demonstrates that, for continuously…

Numerical Analysis · Mathematics 2026-01-19 Thomas Cass , Francesco Piatti , Jeffrey Pei

We study the distributional properties of linear neural networks with random parameters in the context of large networks, where the number of layers diverges in proportion to the number of neurons per layer. Prior works have shown that in…

Machine Learning · Statistics 2024-11-26 Federico Bassetti , Lucia Ladelli , Pietro Rotondo

Neural controlled differential equations (Neural CDEs) are a continuous-time extension of recurrent neural networks (RNNs), achieving state-of-the-art (SOTA) performance at modelling functions of irregular time series. In order to interpret…

Machine Learning · Computer Science 2021-06-22 James Morrill , Patrick Kidger , Lingyi Yang , Terry Lyons

We investigate the mathematical foundations of neural networks in the infinite-width regime through the Neural Tangent Kernel (NTK). We propose the NTK-Eigenvalue-Controlled Residual Network (NTK-ECRN), an architecture integrating Fourier…

Deep neural networks have achieved remarkable success in practice, yet a mechanistic understanding of how features evolve during training remains incomplete, especially in the large-depth limit. For ResNets under depth-$\mu$P scaling, prior…

Machine Learning · Computer Science 2026-05-28 Zihan Yao , Ruoyu Wu , Tianxiang Gao

Random developments of a path into a matrix Lie group $G_N$ have recently been used to construct signature-based kernels on path space. Two examples include developments into GL$(N;\mathbb{R})$ and $U(N;\mathbb{C})$, the general linear and…

Probability · Mathematics 2024-02-20 Thomas Cass , William F. Turner

We analyze feature learning in infinite-width neural networks trained with gradient flow through a self-consistent dynamical field theory. We construct a collection of deterministic dynamical order parameters which are inner-product kernels…

Machine Learning · Statistics 2022-10-05 Blake Bordelon , Cengiz Pehlevan

Controlled ordinary differential equations driven by continuous bounded variation curves can be considered a continuous time analogue of recurrent neural networks for the construction of expressive features of the input curves. We ask up to…

Classical Analysis and ODEs · Mathematics 2025-02-06 Mie Glückstad , Nicola Muca Cirone , Josef Teichmann

We consider the use of Gaussian Processes (GPs) or Neural Networks (NNs) to numerically approximate the solutions to nonlinear partial differential equations (PDEs) with rough forcing or source terms, which commonly arise as pathwise…

Numerical Analysis · Mathematics 2025-01-31 Ricardo Baptista , Edoardo Calvello , Matthieu Darcy , Houman Owhadi , Andrew M. Stuart , Xianjin Yang

We prove that a randomly initialized neural network of *any architecture* has its Tangent Kernel (NTK) converge to a deterministic limit, as the network widths tend to infinity. We demonstrate how to calculate this limit. In prior…

Machine Learning · Statistics 2020-12-01 Greg Yang

In this work, we introduce and study a class of Deep Neural Networks (DNNs) in continuous-time. The proposed architecture stems from the combination of Neural Ordinary Differential Equations (Neural ODEs) with the model structure of…

Systems and Control · Electrical Eng. & Systems 2023-09-18 Daniele Martinelli , Clara Lucía Galimberti , Ian R. Manchester , Luca Furieri , Giancarlo Ferrari-Trecate

Yang (2020a) recently showed that the Neural Tangent Kernel (NTK) at initialization has an infinite-width limit for a large class of architectures including modern staples such as ResNet and Transformers. However, their analysis does not…

Machine Learning · Computer Science 2021-05-11 Greg Yang , Etai Littwin

Kernel conditional mean embeddings (CMEs) offer a powerful framework for representing conditional distribution, but they often face scalability and expressiveness challenges. In this work, we propose a new method that effectively combines…

Machine Learning · Statistics 2024-03-19 Eiki Shimizu , Kenji Fukumizu , Dino Sejdinovic

Recent analyses of neural networks with shaped activations (i.e. the activation function is scaled as the network size grows) have led to scaling limits described by differential equations. However, these results do not a priori tell us…

Machine Learning · Statistics 2024-04-22 Mufan Bill Li , Mihai Nica

Theoretical results show that neural networks can be approximated by Gaussian processes in the infinite-width limit. However, for fully connected networks, it has been previously shown that for any fixed network width, $n$, the Gaussian…

Machine Learning · Statistics 2021-10-28 Mufan Bill Li , Mihai Nica , Daniel M. Roy

Over-parameterized residual networks (ResNets) are amongst the most successful convolutional neural architectures for image processing. Here we study their properties through their Gaussian Process and Neural Tangent kernels. We derive…

Machine Learning · Computer Science 2023-03-02 Daniel Barzilai , Amnon Geifman , Meirav Galun , Ronen Basri

Simulations of complex physical systems are typically realized by discretizing partial differential equations (PDEs) on unstructured meshes. While neural networks have recently been explored for surrogate and reduced order modeling of PDE…

Machine Learning · Computer Science 2021-10-27 Jiayang Xu , Aniruddhe Pradhan , Karthik Duraisamy

Residual deep neural networks are formulated as interacting particle systems leading to a description through neural differential equations, and, in the case of large input data, through mean-field neural networks. The mean-field…

Optimization and Control · Mathematics 2024-03-14 Michael Herty , Chiara Segala , Giuseppe Visconti

Signature kernels, inner products of path signatures, underpin several machine learning algorithms for multivariate time series analysis. For bounded variation paths, signature kernels were recently shown to solve a Goursat PDE. However,…

Machine Learning · Computer Science 2025-06-03 Maud Lemercier , Terry Lyons , Cristopher Salvi

Uncertainty quantification for partial differential equations is traditionally grounded in discretization theory, where solution error is controlled via mesh/grid refinement. Physics-informed neural networks fundamentally depart from this…

Machine Learning · Computer Science 2026-03-20 Amartya Mukherjee , Maxwell Fitzsimmons , David C. Del Rey Fernández , Jun Liu