High-dimensional distribution generation through deep neural networks

DOI10.1007/s42985-021-00115-6OpenAlexW3197005149WikidataQ115369816 ScholiaQ115369816MaRDI QIDQ2062235

Léandre Eberhard, Helmut Bölcskei, Dmytro Perekrestenko

Publication date: 27 December 2021

Published in: SN Partial Differential Equations and Applications (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2107.12466

zbMATH Keywords

neural networksquantizationapproximation theoryspace-filling curvesdeep learninggenerative networks

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Algorithms for approximation of functions (65D15)

Related Items

Approximation bounds for norm constrained neural networks with applications to regression and GANs ⋮ On the capacity of deep generative networks for approximating distributions

Cites Work

• Computational Optimal Transport: With Applications to Data Science
• Multilayer feedforward networks are universal approximators
• Foundations of quantization for probability distributions
• Nonlinear approximation and (deep) ReLU networks
• Optimal transportation between unequal dimensions
• A Note on the Generation of Random Normal Deviates
• Universal approximation bounds for superpositions of a sigmoidal function
• Deep Neural Network Approximation Theory
• Optimal Approximation with Sparsely Connected Deep Neural Networks
• Optimal Transport
• Approximation by superpositions of a sigmoidal function