arXiv Machine Learning

Generalized Splines and Gaussian Processes

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
arXiv Machine Learning
Aug 28

Global universality via discrete-time signatures

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.

By Mihriban Ceylan, David J. Pr\"omel
arXiv Machine Learning
Aug 7

Verifiable Regularity Criterion for Conditional Expectation Operators and Conditional Mean Embeddings with Applications to Nonparametric Regression, Bayesian Inverse Problems, and Koopman Operators

arXiv:2608. 06155v1 Announce Type: cross Abstract: Conditional expectation operators (CEOs) and their associated conditional mean embeddings (CMEs) play a central role across applied mathematics and machine learning, appearing in nonparametric regression, Bayesian inverse problems, and Koopman operator theory.

By Maximiliano Hertel, Ilja Klebanov, Manuel Schaller, Karl Worthmann
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
arXiv Machine Learning
Sep 7

The Sample Complexity of Learning Lipschitz Operators with respect to Gaussian Measures

The paper investigates how many linear samples are needed to learn Lipschitz operators under Gaussian measures. It establishes both lower and upper bounds on the Hermite polynomial approximation error and shows that the minimal worst‑case error cannot converge algebraically with the number of samples. However, if the covariance operator of the Gaussian measure decays rapidly, convergence rates arbitrarily close to any algebraic rate can be achieved.

By Ben Adcock, Michael Griebel, Gregor Maier
arXiv Machine Learning
Jul 28

Minimax Lower Bounds of Kernel Discrepancy Estimation: MMD, HSIC, KSD

arXiv:2607. 24235v1 Announce Type: cross Abstract: Over the past 20 years, kernel discrepancies have been leveraged as a highly powerful tool for quantifying the disagreement of distributions, with numerous successful applications in two-sample, goodness-of-fit, and independence testing, among others.

By Jose Cribeiro-Ramallo, Florian Kalinke, Zolt\'an Szab\'o