English
Related papers

Related papers: Characterizing Model Spaces Among the Finite Dimen…

200 papers

Hierarchical data pervades diverse machine learning applications, including natural language processing, computer vision, and social network analysis. Hyperbolic space, characterized by its negative curvature, has demonstrated strong…

Artificial Intelligence · Computer Science 2026-03-13 Leping Si , Meimei Yang , Hui Xue , Shipeng Zhu , Pengfei Fang

We study a relation between brick $n$-tuples of subspaces of a finite dimensional linear space, and irreducible $n$-tuples of subspaces of a finite dimensional Hilbert (unitary) space such that a linear combination, with positive…

Functional Analysis · Mathematics 2008-07-15 Yu. S. Samoilenko , D. Y. Yakymenko

We present a general framework to learn functions in tensor product reproducing kernel Hilbert spaces (TP-RKHSs). The methodology is based on a novel representer theorem suitable for existing as well as new spectral penalties for tensors.…

Machine Learning · Computer Science 2013-10-21 Marco Signoretto , Lieven De Lathauwer , Johan A. K. Suykens

In this paper, we study the properties of coverings of locally conformally K\"ahler (LCK) spaces with singularities. We begin by proving that a space is LCK if any only if its universal cover is K\"ahler, thereby generalizing a result from…

Differential Geometry · Mathematics 2020-01-22 Ovidiu Preda , Miron Stanciu

We present estimates for the covering numbers of the unit ball of Reproducing Kernel Hilbert Spaces (RKHSs) of functions on $M^d$ a d-dimensional compact two-point homogeneous space. The RKHS is generated by a continuous zonal/isotropic…

Functional Analysis · Mathematics 2026-03-12 Karina Gonzalez , Thaís Jordão

Multiple kernel learning (MKL) algorithms combine different base kernels to obtain a more efficient representation in the feature space. Focusing on discriminative tasks, MKL has been used successfully for feature selection and finding the…

Machine Learning · Computer Science 2019-03-14 Babak Hosseini , Barbara Hammer

Reproducing kernel Hilbert spaces (RKHSs) are special Hilbert spaces where all the evaluation functionals are linear and bounded. They are in one-to-one correspondence with positive definite maps called kernels. Stable RKHSs enjoy the…

Systems and Control · Electrical Eng. & Systems 2023-05-04 Mauro Bisiacco , Gianluigi Pillonetto

The reproducing kernel Hilbert space (RKHS) embedding method is a recently introduced estimation approach that seeks to identify the unknown or uncertain function in the governing equations of a nonlinear set of ordinary differential…

Optimization and Control · Mathematics 2020-07-14 Jia Guo , Sai Tej Paruchuri , Andrew J. Kurdila

Let $H$ be a real Hilbert space. In this short note, using some of the properties of bounded linear operators with closed range defined on $H$, certain bounds for a specific convex subset of the solution set of infinite linear…

Functional Analysis · Mathematics 2020-06-30 Projesh Nath Choudhury , M. Rajesh Kannan , K. C. Sivakumar

We show that every additive category with kernels and cokernels admits a maximal exact structure. Moreover, we discuss two examples of categories of the latter type arising from functional analysis.

Functional Analysis · Mathematics 2014-06-30 Dennis Sieg , Sven-Ake Wegner

We present new classes of positive definite kernels on non-standard spaces that are integrally strictly positive definite or characteristic. In particular, we discuss radial kernels on separable Hilbert spaces, and introduce broad classes…

Machine Learning · Statistics 2022-06-16 Johanna Ziegel , David Ginsbourger , Lutz Dümbgen

We prove metric rigidity for complete manifolds supporting solutions of certain second order differential systems, thus extending classical works on a characterization of space-forms. In the route, we also discover new characterizations of…

Differential Geometry · Mathematics 2009-03-06 Stefano Pigola , Michele Rimoldi

We describe those reproducing kernel Hilbert spaces of holomorphic functions on domains in ${\Bbb C}^d$ for which an analogue of the Nevanlinna-Pick theorem holds, in other words when the existence of a (possibly matrix-valued) function in…

Functional Analysis · Mathematics 2016-10-07 Jim Agler , John E. McCarthy

Computer model calibration involves using partial and imperfect observations of the real world to learn which values of a model's input parameters lead to outputs that are consistent with real-world observations. When calibrating models…

Methodology · Statistics 2023-10-31 Wenzhe Xu , Daniel B. Williamson , Frederic Hourdin , Romain Roehrig

Motivated by the need of processing functional-valued data, or more general, operatorvalued data, we introduce the notion of the operator reproducing kernel Hilbert space (ORKHS). This space admits a unique operator reproducing kernel which…

Functional Analysis · Mathematics 2016-10-23 Rui Wang , Yuesheng Xu

We provide a characterization of the finite dimensionality of vector spaces in terms of the right-sided invertibility of linear operators on them.

Functional Analysis · Mathematics 2021-02-18 Marat V. Markin

In this short note, we will give a generalization of the indefinite Schwarz-Pick inequality due to Seto [8]. Our approach is based on a connection between complex geometry and the geometry of reproducing kernel Hilbert spaces, which was…

Functional Analysis · Mathematics 2024-10-24 Kenta Kojin

We investigate the interaction between the existence of reproducing kernels on infinite-dimensional Hermitian vector bundles and the positivity properties of the corresponding bundles. The positivity refers to the curvature form of certain…

Functional Analysis · Mathematics 2014-02-04 Daniel Beltita , José E. Galé

To help understand various reproducing kernels used in applied sciences, we investigate the inclusion relation of two reproducing kernel Hilbert spaces. Characterizations in terms of feature maps of the corresponding reproducing kernels are…

Functional Analysis · Mathematics 2011-06-22 Haizhang Zhang , Liang Zhao

Deep neural networks excel in high-dimensional problems, outperforming models such as kernel methods, which suffer from the curse of dimensionality. However, the theoretical foundations of this success remain poorly understood. We follow…

Machine Learning · Statistics 2025-10-06 Shuo Huang , Hippolyte Labarrière , Ernesto De Vito , Tomaso Poggio , Lorenzo Rosasco
‹ Prev 1 3 4 5 6 7 10 Next ›