Construction of generalized samplets in Banach spaces

2024-12-01 · Peter Balazs, Michael Multerer

Recently, samplets have been introduced as localized discrete signed measures which are tailored to an underlying data set. Samplets exhibit vanishing moments, i.e., their measure integrals vanish for all polynomials up to a certain degree, which allows for feature detection and data compression. In the present article, we extend the different construction steps of samplets to functionals in Banach spaces more general than point evaluations. To obtain stable representations, we assume that these functionals form frames with square-summable coefficients or even Riesz bases with square-summable coefficients. In either case, the corresponding analysis operator is injective and we obtain samplet bases with the desired properties by means of constructing an isometry of the analysis operator's image. Making the assumption that the dual of the Banach space under consideration is imbedded into the space of compactly supported distributions, the multilevel hierarchy for the generalized samplet construction is obtained by spectral clustering of a similarity graph for the functionals' supports. Based on this multilevel hierarchy, generalized samplets exhibit vanishing moments with respect to a given set of primitives within the Banach space. We derive an abstract localization result for the generalized samplet coefficients with respect to the samplets' support sizes and the approximability of the Banach space elements by the chosen primitives. Finally, we present three examples showcasing the generalized samplet framework.

📄 PDF Abstract BibTeX arXiv:2412.00954

Code (0)

등록된 구현이 없습니다.

Tasks

Data Compression

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Spectral Clustering Spectral clustering has attracted increasing attention due to the promising ability in dealing with nonlinearly separable datasets [15], [16]. In spectral clustering, the…

On Reproducing Kernel Banach Spaces: Generic Definitions and Unified Framework of Constructions

2019-01-04 · Rongrong Lin, Haizhang Zhang, Jun Zhang

Recently, there has been emerging interest in constructing reproducing kernel Banach spaces (RKBS) for applied and theoretical purposes such as machine learning, sampling reconstruction, sparse approximation and function…

BIG-bench Machine Learning

Universal Approximation of Operators with Transformers and Neural Integral Operators

2024-09-01 · Emanuele Zappala, Maryam Bagherian

We study the universal approximation properties of transformers and neural integral operators for operators in Banach spaces. In particular, we show that the transformer architecture is a universal approximator of integr…

Solving Support Vector Machines in Reproducing Kernel Banach Spaces with Positive Definite Functions

2012-09-06 · Gregory E. Fasshauer, Fred J. Hickernell, Qi Ye

In this paper we solve support vector machines in reproducing kernel Banach spaces with reproducing kernels defined on nonsymmetric domains instead of the traditional methods in reproducing kernel Hilbert spaces. Using t…

Generalized support vector regression: duality and tensor-kernel representation

2016-03-18 · Saverio Salzo, Johan A. K. Suykens

In this paper we study the variational problem associated to support vector regression in Banach function spaces. Using the Fenchel-Rockafellar duality theory, we give explicit formulation of the dual problem as well as …

regression

Samplets: A new paradigm for data compression

2021-07-07 · Helmut Harbrecht, Michael Multerer

In this article, we introduce the concept of samplets by transferring the construction of Tausch-White wavelets to the realm of data. This way we obtain a multilevel representation of discrete data which directly enables…