Construction and Monte Carlo estimation of wavelet frames generated by a reproducing kernel

DOI10.1007/S00041-021-09835-0zbMATH Open1462.42051arXiv2006.09870OpenAlexW3154898516MaRDI QIDQ829893FDOQ829893

Authors: Ernesto De Vito, Z. Kereta, Valeriya Naumova, Stefano Vigogna, Lorenzo Rosasco 

Publication date: 6 May 2021

Published in: The Journal of Fourier Analysis and Applications (Search for Journal in Brave)

Abstract: We introduce a construction of multiscale tight frames on general domains. The frame elements are obtained by spectral filtering of the integral operator associated with a reproducing kernel. Our construction extends classical wavelets as well as generalized wavelets on both continuous and discrete non-Euclidean structures such as Riemannian manifolds and weighted graphs. Moreover, it allows to study the relation between continuous and discrete frames in a random sampling regime, where discrete frames can be seen as Monte Carlo estimates of the continuous ones. Pairing spectral regularization with learning theory, we show that a sample frame tends to its population counterpart, and derive explicit finite-sample rates on spaces of Sobolev and Besov regularity. Our results prove the stability of frames constructed on empirical data, in the sense that all stochastic discretizations have the same underlying limit regardless of the set of initial training samples.

Full work available at URL: https://arxiv.org/abs/2006.09870

Recommendations

• scientific article; zbMATH DE number 1928697
• Tight frame expansions of multiscale reproducing kernels in Sobolev spaces
• On construction of multivariate wavelet frames
• Frames of Poisson wavelets on the sphere
• Frames, reproducing kernels, regularization and learning

zbMATH Keywords

waveletslearning theoryregularizationreproducing kernel Hilbert spacesframes

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Nontrigonometric harmonic analysis involving wavelets and other special systems (42C40) Numerical methods for wavelets (65T60) General harmonic expansions, frames (42C15) Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22) Linear operators and ill-posed problems, regularization (47A52)

Cites Work

• Piecewise polynomial, positive definite and compactly supported radial functions of minimal degree
• Diffusion wavelets
• Title not available (Why is that?)
• Wavelets on graphs via spectral graph theory
• Towards a theoretical foundation for Laplacian-based manifold methods
• Title not available (Why is that?)
• Title not available (Why is that?)
• Ten Lectures on Wavelets
• Title not available (Why is that?)
• Finding structure with randomness: probabilistic algorithms for constructing approximate matrix decompositions
• Consistency of spectral clustering
• On early stopping in gradient descent learning
• Optimal rates for the regularized least-squares algorithm
• Title not available (Why is that?)
• Heat kernel generated frames in the setting of Dirichlet spaces
• From graph to manifold Laplacian: the convergence rate
• Title not available (Why is that?)
• Empirical graph Laplacian approximation of Laplace–Beltrami operators: Large sample results
• Learning Theory
• Interpolation of Besov Spaces
• Approximation spaces
• Abstract harmonic analysis of continuous wavelet transforms
• On learning with integral operators
• Universal algorithms for learning theory. I: Piecewise constant functions.
• Decomposition of Hardy Functions into Square Integrable Wavelets of Constant Shape
• Describing functions: Atomic decompositions versus frames
• Continuous frames in Hilbert space
• Painless nonorthogonal expansions
• Continuous frames, function spaces, and the discretization problem
• Band-limited localized Parseval frames and Besov spaces on compact homogeneous manifolds
• Sampling theorems on locally compact groups from oscillation estimates
• Eignets for function approximation on manifolds
• Diffusion polynomial frames on metric measure spaces
• Geometric space-frequency analysis on manifolds
• Concentration inequalities and moment bounds for sample covariance operators
• Frames and other bases in abstract and function spaces. Novel methods in harmonic analysis. Volume 1
• Optimal rates for regularization of statistical inverse learning problems
• Spectral convergence of the connection Laplacian from random samples
• Sparse representation on graphs by tight wavelet frames and applications
• The discretization problem for continuous frames
• Error estimates for spectral convergence of the graph Laplacian on random geometric graphs toward the Laplace-Beltrami operator
• Tight framelets and fast framelet filter bank transforms on manifolds
• Hierarchically compositional kernels for scalable nonparametric learning
• Fast approximate truncated SVD

Cited In (6)

• Reproducing kernel bounds for an advanced wavelet frame via the theta function
• Diffusion polynomial frames on metric measure spaces
• Discretizing \(L_p\) norms and frame theory
• Randomized signal processing with continuous frames
• \textsf{StreaMRAK} a streaming multi-resolution adaptive kernel algorithm
• Overview of the topical collection: harmonic analysis on combinatorial graphs

This page was built for publication: Construction and Monte Carlo estimation of wavelet frames generated by a reproducing kernel

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q829893)