A convenient infinite dimensional framework for generative adversarial learning

DOI10.1214/23-EJS2104MaRDI QIDQ2683193

Matthias Rottmann, Hayk Asatryan, Hanno Gottschalk, Marieke Lippert

Publication date: 3 February 2023

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2011.12087

zbMATH Keywords

statistical learning theorychainingcovering numbers for Hölder spacesgenerative adversarial learninginverse Rosenblatt transformation

Mathematics Subject Classification ID

Asymptotic properties of nonparametric inference (62G20) Learning and adaptive systems in artificial intelligence (68T05)

Uses Software

• CycleGAN
• pix2pix
• NICE
• CopulaModel
• Wasserstein GAN

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Partial differential equations. I: Basic theory
• Elliptic partial differential equations of second order
• Weak convergence and empirical processes. With applications to statistics
• Optimal approximation of piecewise smooth functions using deep ReLU neural networks
• Some theoretical properties of GANs
• Error bounds for approximations with deep ReLU networks
• Dependence Modeling with Copulas
• Mathematical Foundations of Infinite-Dimensional Statistical Models
• Polar factorization and monotone rearrangement of vector‐valued functions
• Equivalence of approximation by convolutional neural networks and fully-connected networks
• Advanced Lectures on Machine Learning
• Understanding Machine Learning
• Monte Carlo sampling methods using Markov chains and their applications
• Probability-1
• Remarks on a Multivariate Transformation