New boundaries for positive definite functions

Publication date 27 November 2019

Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Learning and adaptive systems in artificial intelligence (68T05) Graphs and linear algebra (matrices, eigenvalues, etc.) (05C50) Applications of functional analysis in probability theory and statistics (46N30) Structural characterization of families of graphs (05C75) Applications of Lie groups to the sciences; explicit representations (22E70) General harmonic expansions, frames (42C15) Applications of functional analysis to differential and integral equations (46N20) Applications of functional analysis in quantum physics (46N50) Diffusion processes and stochastic analysis on manifolds (58J65) Numerical methods for integral transforms (65R10) Potentials and capacity, harmonic measure, extremal length and related notions in two dimensions (31A15) Discrete potential theory (31C20) Quantum stochastic calculus (81S25) Algebras of unbounded operators; partial algebras of operators (47L60)

Abstract: With view to applications in stochastic analysis and geometry, we introduce a new correspondence for positive definite kernels (p.d.)

K

and their associated reproducing kernel Hilbert spaces. With this we establish two kinds of factorizations: (i) Probabilistic: Starting with a positive definite kernel

K

we analyze associated Gaussian processes

V

. Properties of the Gaussian processes will be derived from certain factorizations of

K

, arising as a covariance kernel of

V

. (ii) Geometric analysis: We discuss families of measure spaces arising as boundaries for

K

. Our results entail an analysis of a partial order on families of p.d. kernels, a duality for operators and frames, optimization, Karhunen--Lo`eve expansions, and factorizations. Applications include a new boundary analysis for the Drury-Arveson kernel, and for certain fractals arising as iterated function systems; and an identification of optimal feature spaces in machine learning models.

This page was built for publication: New boundaries for positive definite functions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6329993)