English
Related papers

Related papers: Positive definite kernels and boundary spaces

200 papers

We implement an all-optical setup demonstrating kernel-based quantum machine learning for two-dimensional classification problems. In this hybrid approach, kernel evaluations are outsourced to projective measurements on suitably designed…

We give a complete description of the boundary behaviour of the Poisson kernel and the harmonic Bergman kernel of a bounded domain with smooth boundary, which in some sense is an analogue of the similar description for the usual Bergman…

Classical Analysis and ODEs · Mathematics 2015-03-24 Miroslav Englis

We generalize the characterization theorem going back to Mercer and Young, which states that a symmetric and continuous kernel is positive definite if and only if it is integrally positive definite, to matrix-valued kernels on separable…

Functional Analysis · Mathematics 2025-10-09 Eyal Neuman , Sturmius Tuschmann

Kernel methods are powerful tools in machine learning. Classical kernel methods are based on positive-definite kernels, which map data spaces into reproducing kernel Hilbert spaces (RKHS). For non-Euclidean data spaces, positive-definite…

Machine Learning · Computer Science 2024-07-31 Nathael Da Costa , Cyrus Mostajeran , Juan-Pablo Ortega , Salem Said

A device called a 'Gaussian Boson Sampler' has initially been proposed as a near-term demonstration of classically intractable quantum computation. As recently shown, it can also be used to decide whether two graphs are isomorphic. Based on…

Quantum Physics · Physics 2020-03-18 Maria Schuld , Kamil Brádler , Robert Israel , Daiqin Su , Brajesh Gupt

Hilbert-Schmidt independence criterion and distance covariance are methods to describe independence of random variables using either the Kronecker product of positive definite kernels or the Kronecker product of conditionally negative…

Functional Analysis · Mathematics 2022-01-05 Jean Carlo Guella

Positive-definite kernel functions are fundamental elements of kernel methods and Gaussian processes. A well-known construction of such functions comes from Bochner's characterization, which connects a positive-definite function with a…

Machine Learning · Statistics 2016-10-28 Jie Chen , Dehua Cheng , Yan Liu

We consider determinantal point processes on a compact complex manifold X in the limit of many particles. The correlation kernels of the processes are the Bergman kernels associated to a a high power of a given Hermitian holomorphic line…

Complex Variables · Mathematics 2016-12-15 Robert J. Berman

Reproducing kernel Hilbert spaces are elucidated without assuming prior familiarity with Hilbert spaces. Compared with extant pedagogic material, greater care is placed on motivating the definition of reproducing kernel Hilbert spaces and…

History and Overview · Mathematics 2015-11-06 Jonathan H. Manton , Pierre-Olivier Amblard

Gaussian process regression is a widely-applied method for function approximation and uncertainty quantification. The technique has gained popularity recently in the machine learning community due to its robustness and interpretability. The…

Machine Learning · Statistics 2022-10-12 Marcus M. Noack , James A. Sethian

The heat kernel on the symmetric space of positive definite Hermitian matrices is used to endow the spaces of Bergman metrics of degree k on a Riemann surface M with a family of probability measures depending on a choice of the background…

Probability · Mathematics 2016-08-10 Semyon Klevtsov , Steve Zelditch

Modern Bayesian optimization and adaptive sampling methods increasingly rely on nonlinear parametric models, yet theoretical guarantees for such models under adaptive data collection remain limited. Existing analyses largely focus on…

Machine Learning · Statistics 2026-05-14 Rafael Oliveira

This paper proposes some extensions to the work on kernels dedicated to string or time series global alignment based on the aggregation of scores obtained by local alignments. The extensions we propose allow to construct, from classical…

Machine Learning · Computer Science 2015-03-17 Pierre-François Marteau , Sylvie Gibet

We prove optimal estimates of the Bergman and Szeg\H{o} kernels on the diagonal, and the Bergman metric near the boundary of bounded smooth generalized decoupled pseudoconvex domains in $\mathbb{C}^n$. The generalized decoupled domains we…

Complex Variables · Mathematics 2023-12-21 Ravi Shankar Jaiswal

Complex-valued signals are used in the modeling of many systems in engineering and science, hence being of fundamental interest. Often, random complex-valued signals are considered to be proper. A proper complex random variable or process…

Machine Learning · Computer Science 2015-02-19 Rafael Boloix-Tortosa , F. Javier Payán-Somet , Eva Arias-de-Reyna , Juan José Murillo-Fuentes

For a class of one-dimensional determinantal point processes including those induced by orthogonal projections with integrable kernels satisfying a growth condition, it is proved that their conditional measures, with respect to the…

Probability · Mathematics 2016-05-05 Alexander I. Bufetov

Gaussian processes are flexible function approximators, with inductive biases controlled by a covariance kernel. Learning the kernel is the key to representation learning and strong predictive performance. In this paper, we develop…

Machine Learning · Computer Science 2019-10-31 Gregory W. Benton , Wesley J. Maddox , Jayson P. Salkey , Julio Albinati , Andrew Gordon Wilson

Given a reproducing kernel $k$ on a nonempty set $X$, we define the reproductive boundary of $X$ with respect to $k$. Furthermore, we generalize the well known nontangential and horocyclic approach regions of the unit circle to this new…

Functional Analysis · Mathematics 2025-10-14 Frej Dahlin

This is a survey of results about permanental processes, real valued positive processes which are a generalization of squares of Gaussian processes. In a certain sense the symmetric positive definite function that determines a Gaussian…

Probability · Mathematics 2010-08-23 Hana Kogan , Michael B. Marcus , Jay Rosen

Quantum computing algorithms have been shown to produce performant quantum kernels for machine-learning classification problems. Here, we examine the performance of quantum kernels for regression problems of practical interest. For an…

Quantum Physics · Physics 2024-09-30 Xuyang Guo , Jun Dai , Roman V. Krems