Approximation of Lipschitz Functions Using Deep Spline Neural Networks

DOI10.1137/22m1504573arXiv2204.06233OpenAlexW4377043292MaRDI QIDQ6104312

Alexis Goujon, Michael Unser, Pakshal Bohra, Sebastian Neumayer

Publication date: 28 June 2023

Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2204.06233

zbMATH Keywords

robustnessuniversalityLipschitz continuitydeep learninglinear splineslearnable activations

Mathematics Subject Classification ID

Numerical computation using splines (65D07) Lipschitz (Hölder) classes (26A16) Approximation with constraints (41A29) Spline approximation (41A15) Information theory (general) (94A15) General topics in artificial intelligence (68T01) Representation and superposition of functions (26B40)

Related Items (2)

Stable parameterization of continuous and piecewise-linear functions ⋮ On the number of regions of piecewise linear neural networks

Cites Work

• Unnamed Item
• A representation method for PWL functions oriented to parallel processing
• Parseval proximal neural networks
• CLIP: cheap Lipschitz training of neural networks
• Regularisation of neural networks by enforcing Lipschitz continuity
• Convolutional proximal neural networks and plug-and-play algorithms
• Stabilizing Invertible Neural Networks Using Mixture Models
• Deep Neural Networks With Trainable Activations and Controlled Lipschitz Constant
• Higher-order total variation approaches and generalisations
• Deep Learning Architectures

This page was built for publication: Approximation of Lipschitz Functions Using Deep Spline Neural Networks