Operator-Valued Kernels, Machine Learning, and Dynamical Systems

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Jorgensen, Palle E. T., Tian, James
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929537027145728
author Jorgensen, Palle E. T.
Tian, James
author_facet Jorgensen, Palle E. T.
Tian, James
contents In the context of kernel optimization, we prove a result that yields new factorizations and realizations. Our initial context is that of general positive operator-valued kernels. We further present implications for Hilbert space-valued Gaussian processes, as they arise in applications to dynamics and to machine learning. Further applications are given in non-commutative probability theory, including a new non-commutative Radon--Nikodym theorem.
format Preprint
id arxiv_https___arxiv_org_abs_2405_09315
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Operator-Valued Kernels, Machine Learning, and Dynamical Systems
Jorgensen, Palle E. T.
Tian, James
Operator Algebras
Mathematical Physics
Functional Analysis
Quantum Physics
Primary: 81P15, secondary: 46E22, 46L53, 47A20, 60G15, 68T07, 81P47
In the context of kernel optimization, we prove a result that yields new factorizations and realizations. Our initial context is that of general positive operator-valued kernels. We further present implications for Hilbert space-valued Gaussian processes, as they arise in applications to dynamics and to machine learning. Further applications are given in non-commutative probability theory, including a new non-commutative Radon--Nikodym theorem.
title Operator-Valued Kernels, Machine Learning, and Dynamical Systems
topic Operator Algebras
Mathematical Physics
Functional Analysis
Quantum Physics
Primary: 81P15, secondary: 46E22, 46L53, 47A20, 60G15, 68T07, 81P47
url https://arxiv.org/abs/2405.09315