Signature asymptotics, empirical processes, and optimal transport

DOI10.1214/23-EJP1048arXiv2107.11203OpenAlexW3184555774MaRDI QIDQ6136798FDOQ6136798

Author name not available (Why is that?), Thomas Cass, Remy Messadene

Publication date: 17 January 2024

Published in: Electronic Journal of Probability (Search for Journal in Brave)

Abstract: Rough path theory provides one with the notion of signature, a graded family of tensors which characterise, up to a negligible equivalence class, and ordered stream of vector-valued data. In the last few years, use of the signature has gained traction in time-series analysis, machine learning , deep learning and more recently in kernel methods. In this article, we lay down the theoretical foundations for a connection between signature asymptotics, the theory of empirical processes, and Wasserstein distances, opening up the landscape and toolkit of the second and third in the study of the first. Our main contribution is to show that the Hambly-Lyons limit can be reinterpreted as a statement about the asymptotic behaviour of Wasserstein distances between two independent empirical measures of samples from the same underlying distribution. In the setting studied here, these measures are derived from samples from a probability distribution which is determined by geometrical properties of the underlying path. The general question of rates of convergence for these objects has been studied in depth in the recent monograph of Bobkov and Ledoux. By using these results, we generalise the original result of Hambly and Lyons from $C^3$ curves to a broad class of $C^2$ ones. We conclude by providing an explicit way to compute the limit in terms of a second-order differential equation.

Full work available at URL: https://arxiv.org/abs/2107.11203

zbMATH Keywords

optimal transportempirical processessignaturesrough analysis

Mathematics Subject Classification ID

Signatures and data streams (60L10)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• The signature of a rough path: uniqueness
• Stratonovich's signatures of Brownian motion determine Brownian sample paths
• On an inversion theorem for Stratonovich's signatures of multidimensional diffusion paths
• The uniqueness of signature problem in the non-Markov setting
• Uniqueness for the signature of a path of bounded variation and the reduced path group
• Differential equations driven by rough paths. Ecole d'Eté de Probabilités de Saint-Flour XXXIV -- 2004. Lectures given at the 34th probability summer school, July 6--24, 2004.
• Asymptotics for \(L_2\) functionals of the empirical quantile process, with applications to tests of fit based on weighted Wasserstein distances
• One-dimensional empirical measures, order statistics, and Kantorovich transport distances
• Strong approximations of the quantile process
• Characteristic functions of measures on geometric rough paths
• Inverting the signature of a path
• Hyperbolic development and inversion of signature
• Tail asymptotics of the Brownian signature
• A non-vanishing property for the signature of a path
• Super-multiplicativity and a lower bound for the decay of the signature of a path of finite length
• Kernels for sequentially ordered data
• A course on rough paths. With an introduction to regularity structures
• Path developments and tail asymptotics of signature for pure rough paths
• Reconstruction for the signature of a rough path
• The Signature Kernel Is the Solution of a Goursat PDE

This page was built for publication: Signature asymptotics, empirical processes, and optimal transport

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6136798)