Signature asymptotics, empirical processes, and optimal transport
From MaRDI portal
Publication:6136798
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 curves to a broad class of ones. We conclude by providing an explicit way to compute the limit in terms of a second-order differential equation.
Recommendations
- Characteristic functions of measures on geometric rough paths
- Tail asymptotics of the Brownian signature
- The uniqueness of signature problem in the non-Markov setting
- Asymptotic behavior of Wasserstein distance for weighted empirical measures of diffusion processes on compact Riemannian manifolds
- Concentration and exact convergence rates for expected Brownian signatures
Cites work
- scientific article; zbMATH DE number 3820918 (Why is no real title available?)
- scientific article; zbMATH DE number 1245556 (Why is no real title available?)
- scientific article; zbMATH DE number 3274494 (Why is no real title available?)
- A course on rough paths. With an introduction to regularity structures
- A non-vanishing property for the signature of a path
- Asymptotics for \(L_2\) functionals of the empirical quantile process, with applications to tests of fit based on weighted Wasserstein distances
- Characteristic functions of measures on geometric rough paths
- 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.
- Hyperbolic development and inversion of signature
- Inverting the signature of a path
- Kernels for sequentially ordered data
- On an inversion theorem for Stratonovich's signatures of multidimensional diffusion paths
- One-dimensional empirical measures, order statistics, and Kantorovich transport distances
- Path developments and tail asymptotics of signature for pure rough paths
- Reconstruction for the signature of a rough path
- Stratonovich's signatures of Brownian motion determine Brownian sample paths
- Strong approximations of the quantile process
- Super-multiplicativity and a lower bound for the decay of the signature of a path of finite length
- Tail asymptotics of the Brownian signature
- The signature kernel is the solution of a Goursat PDE
- The signature of a rough path: uniqueness
- 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
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)
