Construction of generalized samplets in Banach spaces

• URL: http://arxiv.org/abs/2412.00954v1
• Date: Sun, 01 Dec 2024 20:14:37 GMT
• Title: Construction of generalized samplets in Banach spaces
• Authors: Peter Balazs, Michael Multerer,
• Abstract summary: We extend the different steps of samplets to functionals in Banach spaces more than point evaluations. We derive an abstract localization result for the generalized samplet coefficients with respect to the samplets' support and the approximability of the Banach space elements.
• Score: 0.0
• License:
• Abstract: 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.

Related papers

• How Do Flow Matching Models Memorize and Generalize in Sample Data Subspaces? [10.315743300140966]
  Real-world data is often assumed to lie within a low-dimensional structure embedded in high-dimensional space. In practical settings, we observe only a finite set of samples, forming what we refer to as the sample data subspace. A major challenge lies in whether generative models can reliably synthesize samples that stay within this subspace.
  arXiv  Detail & Related papers  (2024-10-31T03:08:07Z)
• Unified Convergence Analysis for Score-Based Diffusion Models with Deterministic Samplers [49.1574468325115]
  We introduce a unified convergence analysis framework for deterministic samplers. Our framework achieves iteration complexity of $tilde O(d2/epsilon)$. We also provide a detailed analysis of Denoising Implicit Diffusion Models (DDIM)-type samplers.
  arXiv  Detail & Related papers  (2024-10-18T07:37:36Z)
• Multiscale scattered data analysis in samplet coordinates [0.0]
  We study multiscale data scattered schemes for globally supported radial basis functions. We suggest to represent the resulting generalized Vandermonde matrices in samplet coordinates. We prove that the condition numbers of the linear systems at each level remain bounded independent of the particular level.
  arXiv  Detail & Related papers  (2024-09-23T08:07:47Z)
• Conformal inference for regression on Riemannian Manifolds [49.7719149179179]
  We investigate prediction sets for regression scenarios when the response variable, denoted by $Y$, resides in a manifold, and the covariable, denoted by X, lies in Euclidean space. We prove the almost sure convergence of the empirical version of these regions on the manifold to their population counterparts.
  arXiv  Detail & Related papers  (2023-10-12T10:56:25Z)
• Wrapped Distributions on homogeneous Riemannian manifolds [58.720142291102135]
  Control over distributions' properties, such as parameters, symmetry and modality yield a family of flexible distributions. We empirically validate our approach by utilizing our proposed distributions within a variational autoencoder and a latent space network model.
  arXiv  Detail & Related papers  (2022-04-20T21:25:21Z)
• Sensing Cox Processes via Posterior Sampling and Positive Bases [56.82162768921196]
  We study adaptive sensing of point processes, a widely used model from spatial statistics. We model the intensity function as a sample from a truncated Gaussian process, represented in a specially constructed positive basis. Our adaptive sensing algorithms use Langevin dynamics and are based on posterior sampling (textscCox-Thompson) and top-two posterior sampling (textscTop2) principles.
  arXiv  Detail & Related papers  (2021-10-21T14:47:06Z)
• Nested sampling with any prior you like [0.0]
  Bijectors trained on samples from a desired prior density provide a general-purpose method for constructing transformations. We demonstrate the use of trained bijectors in conjunction with nested sampling on a number of examples from cosmology.
  arXiv  Detail & Related papers  (2021-02-24T18:45:13Z)
• Construction and Monte Carlo estimation of wavelet frames generated by a reproducing kernel [14.207723862182947]
  We introduce a construction of multiscale tight frames on general domains. We extend classical wavelets as well as generalized wavelets on non-Euclidean structures. We show that a sample frame tends to its population counterpart, and derive explicit finite-sample rates on spaces of Sobolev and Besov regularity.
  arXiv  Detail & Related papers  (2020-06-17T13:51:11Z)
• Twisted Fourier analysis and pseudo-probability distributions [1.5555393702795075]
  We use a noncommutative generalization of Fourier analysis to define a broad class of pseudo-probability representations. We find Wigner representations for fermions, hard-core bosons, and angle-number systems.
  arXiv  Detail & Related papers  (2020-04-28T21:39:27Z)
• Efficiently Sampling Functions from Gaussian Process Posteriors [76.94808614373609]
  We propose an easy-to-use and general-purpose approach for fast posterior sampling. We demonstrate how decoupled sample paths accurately represent Gaussian process posteriors at a fraction of the usual cost.
  arXiv  Detail & Related papers  (2020-02-21T14:03:16Z)
• Distributed, partially collapsed MCMC for Bayesian Nonparametrics [68.5279360794418]
  We exploit the fact that completely random measures, which commonly used models like the Dirichlet process and the beta-Bernoulli process can be expressed as, are decomposable into independent sub-measures. We use this decomposition to partition the latent measure into a finite measure containing only instantiated components, and an infinite measure containing all other components. The resulting hybrid algorithm can be applied to allow scalable inference without sacrificing convergence guarantees.
  arXiv  Detail & Related papers  (2020-01-15T23:10:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.