English
Related papers

Related papers: Log-PDE Methods for Rough Signature Kernels

200 papers

Recently, there has been an increased interest in the development of kernel methods for learning with sequential data. The signature kernel is a learning tool with potential to handle irregularly sampled, multivariate time series. In…

Analysis of PDEs · Mathematics 2021-09-30 Cristopher Salvi , Thomas Cass , James Foster , Terry Lyons , Weixin Yang

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

Central to rough path theory is the signature transform of a path, an infinite series of tensors given by the iterated integrals of the underlying path. The signature poses an effective way to capture sequentially ordered information,…

Numerical Analysis · Mathematics 2024-12-18 Daniil Shmelev , Cristopher Salvi

The expected signature kernel arises in statistical learning tasks as a similarity measure of probability measures on path space. Computing this kernel for known classes of stochastic processes is an important problem that, in particular,…

Probability · Mathematics 2025-09-10 Peter K. Friz , Paul P. Hager

The signature kernel is a recent state-of-the-art tool for analyzing high-dimensional sequential data, valued for its theoretical guarantees and strong empirical performance. In this paper, we present a novel method for efficiently…

Numerical Analysis · Mathematics 2025-11-12 Matthew Tamayo-Rios , Alexander Schell , Rima Alaifari

We develop a kernel-based solver for path-dependent PDEs (PPDEs) along with a convergence theory. Our numerical scheme leverages signature kernels, a recently introduced class of kernels on path-space. Specifically, we solve an optimal…

Numerical Analysis · Mathematics 2026-03-17 Alexandre Pannier , Cristopher Salvi

This article provides a concise overview of some of the recent advances in the application of rough path theory to machine learning. Controlled differential equations (CDEs) are discussed as the key mathematical model to describe the…

Machine Learning · Computer Science 2023-02-10 Adeline Fermanian , Terry Lyons , James Morrill , Cristopher Salvi

Building on the functional-analytic framework of operator-valued kernels and un-truncated signature kernels, we propose a scalable, provably convergent signature-based algorithm for a broad class of high-dimensional, path-dependent hedging…

Functional Analysis · Mathematics 2025-02-06 Nicola Muca Cirone , Cristopher Salvi

We develop a branched signature kernel solver for linear and nonlinear ordinary differential equations driven by a \emph{single observed trajectory} of a possibly rough forcing signal -- a setting that arises naturally in earthquake…

Numerical Analysis · Mathematics 2026-05-26 Munawar Ali , Qi Feng , Charlie Pyle , George Xu

The interface between stochastic analysis and machine learning is a rapidly evolving field, with path signatures - iterated integrals that provide faithful, hierarchical representations of paths - offering a principled and universal feature…

Machine Learning · Statistics 2025-06-26 Csaba Tóth

We tackle high-dimensional, path-dependent valuation and control and introduce a deep BSDE/2BSDE solver that couples truncated log-signatures with a neural rough differential equation (RDE) backbone. The architecture aligns stochastic…

Mathematical Finance · Quantitative Finance 2025-11-04 Ali Atiah Alzahrani

We develop a rough-path framework for two-parameter rough differential equations on rectangular and simplicial domains, motivated by the signature kernel and Schwinger--Dyson kernel equations. The theory is formulated in spaces of jointly…

Probability · Mathematics 2026-05-12 Thomas Cass , Dan Crisan , Andrea Iannucci , William F. Turner

Rough path theory is focused on capturing and making precise the interactions between highly oscillatory and non-linear systems. It draws on the analysis of LC Young and the geometric algebra of KT Chen. The concepts and the uniform…

Probability · Mathematics 2014-05-20 Terry Lyons

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

Using a combination of recurrent neural networks and signature methods from the rough paths theory we design efficient algorithms for solving parametric families of path dependent partial differential equations (PPDEs) that arise in pricing…

Computational Finance · Quantitative Finance 2020-11-24 Marc Sabate-Vidales , David Šiška , Lukasz Szpruch

This article presents a three-step framework for learning and solving partial differential equations (PDEs) using kernel methods. Given a training set consisting of pairs of noisy PDE solutions and source/boundary terms on a mesh, kernel…

Machine Learning · Statistics 2023-04-03 Da Long , Nicole Mrvaljevic , Shandian Zhe , Bamdad Hosseini

Developing efficient numerical algorithms for the solution of high dimensional random Partial Differential Equations (PDEs) has been a challenging task due to the well-known curse of dimensionality. We present a new solution framework for…

Machine Learning · Computer Science 2019-10-17 Mohammad Amin Nabian , Hadi Meidani

We propose a deep signature/log-signature FBSDE algorithm to solve forward-backward stochastic differential equations (FBSDEs) with state and path dependent features. By incorporating the deep signature/log-signature transformation into the…

Machine Learning · Computer Science 2022-08-22 Qi Feng , Man Luo , Zhaoyu Zhang

Neural SDEs are continuous-time generative models for sequential data. State-of-the-art performance for irregular time series generation has been previously obtained by training these models adversarially as GANs. However, as typical for…

Machine Learning · Statistics 2023-05-26 Zacharia Issa , Blanka Horvath , Maud Lemercier , Cristopher Salvi

Neural controlled differential equations (CDEs) are the continuous-time analogue of recurrent neural networks, as Neural ODEs are to residual networks, and offer a memory-efficient continuous-time way to model functions of potentially…

Machine Learning · Computer Science 2021-06-22 James Morrill , Cristopher Salvi , Patrick Kidger , James Foster , Terry Lyons
‹ Prev 1 2 3 10 Next ›