← Back to all news
arXiv Machine Learning By Mihriban Ceylan, David J. Pr\"omel

Global universality via discrete-time signatures

Read the original on arXiv Machine Learning →

The paper proves global universal approximation theorems for non‑anticipative and general path‑dependent functionals on spaces of piecewise linear paths, showing that linear functionals of the corresponding signatures are dense in $L^p$ and weighted norms. It demonstrates that these results apply to piecewise linear interpolations of Gaussian processes, including Brownian motion and fractional Brownian motion with Hurst parameter $H>1/4$, and provides quantitative convergence rates for signatures of such approximations toward their continuous‑time counterparts. Consequently, the authors obtain $L^p$‑approximation results for path‑dependent functionals of Gaussian processes and for random ordinary and stochastic differential equations driven by Brownian motion.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Jul 7

Global universal approximation with Brownian signatures

arXiv:2512. 16396v2 Announce Type: replace-cross Abstract: We establish $L^p$-universal approximation theorems for general path-dependent and non-anticipative functionals on suitable rough path spaces, showing that linear functionals acting on signatures of time-extended rough paths are dense with respect to the $L^p$-distance.

By Mihriban Ceylan, David J. Pr\"omel
More like this →
arXiv Machine Learning
Aug 31

Generalized Splines and Gaussian Processes

arXiv:2608.28446v1 Announce Type: cross Abstract: For finite-dimensional linear inverse problems where the variables are Gaussian, it is well-known that the minimum-mean-square error estimator takes...

By Michael Unser
More like this →
arXiv Statistics ML
Oct 16

Expected Signature Kernels for Rough Paths

The paper introduces the expected signature kernel as a similarity measure for probability laws on path space, directly applicable to signature maximum mean discrepancies. It characterizes this kernel for group-valued inhomogeneous Lévy processes by solving an extended Goursat-type system, providing exact solutions in the continuous case and well‑posed infinite‑dimensional systems with error‑controlled truncations for jump processes. The authors also show that conditioning on sampled quadratic variations yields an unbiased, lower‑variance statistic for conditionally Gaussian martingales, and present computable finite‑grid implementations that improve variance and test power.

By Peter K. Friz, Paul P. Hager
More like this →
arXiv Machine Learning
Aug 28

Gaussian Processes and Reproducing Kernel Hilbert Spaces: Connections and Equivalences

The monograph explores the relationships between Gaussian processes and reproducing kernel Hilbert spaces (RKHS), two widely used approaches that rely on positive definite kernels. It examines how these frameworks connect and are equivalent across key topics such as regression, interpolation, numerical integration, distributional discrepancies, statistical dependence, and Gaussian process sample path properties. By establishing a unifying perspective based on the equivalence between the Gaussian Hilbert space and the RKHS, the work aims to bridge methods developed independently by the machine learning, statistics, and numerical analysis communities.

By Motonobu Kanagawa, Philipp Hennig, Dino Sejdinovic, Bharath K. Sriperumbudur
More like this →