Stable parameterization of continuous and piecewise-linear functions

DOI10.1016/j.acha.2023.101581arXiv2203.05261OpenAlexW4385652243MaRDI QIDQ6051165

Alexis Goujon, Joaquim Campos, Michael Unser

Publication date: 19 September 2023

Published in: Applied and Computational Harmonic Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2203.05261

zbMATH Keywords

triangulationRiesz basiscondition numberLipschitz continuityhat basis functionsReLU neural networkscontinuous and piecewise-linear functionlinear box splinestable parameterization

Mathematics Subject Classification ID

Numerical analysis (65-XX) Computer science (68-XX)

Related Items (1)

On the number of regions of piecewise linear neural networks

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Symmetric box-splines on the \(\mathcal A^*_n\) lattice
• B-splines from parallelepipeds
• The Delaunay triangulation learner and its ensembles
• Triangulations. Structures for algorithms and applications
• Translates of multivariate splines
• Box splines
• Optimality of the Delaunay triangulation in \(\mathbb{R}^ d\)
• Characterization of compactly supported refinable splines whose shifts form a Riesz basis
• Regularisation of neural networks by enforcing Lipschitz continuity
• Locally piecewise affine functions and their order structure
• Deep vs. shallow networks: An approximation theory perspective
• On Circulant Matrices
• Riesz bases of wavelets and applications to numerical solutions of elliptic equations
• How to integrate a polynomial over a simplex
• [https://portal.mardi4nfdi.de/wiki/Publication:3146552 The Multi-Dimensional Version of � b a x p dx]
• Conditioning of finite element equations with arbitrary anisotropic meshes
• Relu Deep Neural Networks and Linear Finite Elements
• Generalization of Hinging Hyperplanes
• Some Combinatorial Lemmas in Topology
• On the Linear Independence of Multivariate B-Splines, I. Triangulations of Simploids
• Facing up to arrangements: face-count formulas for partitions of space by hyperplanes
• Approximation from Shift-Invariant Subspaces of L 2 (ℝ d )
• Sampling procedures in function spaces and asymptotic equivalence with shannon's sampling theory
• On the approximation power of convolution-based least squares versus interpolation
• Robust Large Margin Deep Neural Networks
• Oblique projections in atomic spaces
• Stabilizing Invertible Neural Networks Using Mixture Models
• On Lipschitz Bounds of General Convolutional Neural Networks
• CONTINUOUS PIECEWISE LINEAR FUNCTIONS
• Approximation of Lipschitz Functions Using Deep Spline Neural Networks

This page was built for publication: Stable parameterization of continuous and piecewise-linear functions