Sensitivity-Aware Density Estimation in Multiple Dimensions

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Boquet-Pujadas, Aleix, Pla, Pol del Aguila, Unser, Michael
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912410917404672
author Boquet-Pujadas, Aleix
Pla, Pol del Aguila
Unser, Michael
author_facet Boquet-Pujadas, Aleix
Pla, Pol del Aguila
Unser, Michael
contents We formulate an optimization problem to estimate probability densities in the context of multidimensional problems that are sampled with uneven probability. It considers detector sensitivity as an heterogeneous density and takes advantage of the computational speed and flexible boundary conditions offered by splines on a grid. We choose to regularize the Hessian of the spline via the nuclear norm to promote sparsity. As a result, the method is spatially adaptive and stable against the choice of the regularization parameter, which plays the role of the bandwidth. We test our computational pipeline on standard densities and provide software. We also present a new approach to PET rebinning as an application of our framework.
format Preprint
id arxiv_https___arxiv_org_abs_2506_02323
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Sensitivity-Aware Density Estimation in Multiple Dimensions
Boquet-Pujadas, Aleix
Pla, Pol del Aguila
Unser, Michael
Machine Learning
Artificial Intelligence
Computational Engineering, Finance, and Science
Data Structures and Algorithms
Signal Processing
We formulate an optimization problem to estimate probability densities in the context of multidimensional problems that are sampled with uneven probability. It considers detector sensitivity as an heterogeneous density and takes advantage of the computational speed and flexible boundary conditions offered by splines on a grid. We choose to regularize the Hessian of the spline via the nuclear norm to promote sparsity. As a result, the method is spatially adaptive and stable against the choice of the regularization parameter, which plays the role of the bandwidth. We test our computational pipeline on standard densities and provide software. We also present a new approach to PET rebinning as an application of our framework.
title Sensitivity-Aware Density Estimation in Multiple Dimensions
topic Machine Learning
Artificial Intelligence
Computational Engineering, Finance, and Science
Data Structures and Algorithms
Signal Processing
url https://arxiv.org/abs/2506.02323