MR-GAN: Manifold Regularized Generative Adversarial Networks for Scientific Data

DOI10.1137/20M1344299MaRDI QIDQ5018897zbMATH OpenOpenAlexFDO

Authors

Publication date 27 December 2021

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

Full work available at URL https://doi.org/10.1137/20m1344299

zbMATH Keywords

GANsgenerative modelingmanifoldscientific MLunsupervised

Mathematics Subject Classification ID

Artificial intelligence (68T99) Minimax problems in mathematical programming (90C47) Other game-theoretic models (91A40)

Recommendations

• Disentangled Representation Learning and Generation With Manifold Optimization
• Deep Generative Models and Inverse Problems
• A convenient infinite dimensional framework for generative adversarial learning
• GADE: a generative adversarial approach to density estimation and its applications
• Inferential Wasserstein Generative Adversarial Networks
• Manifold adversarial training for supervised and semi-supervised learning
• GAT–GMM: Generative Adversarial Training for Gaussian Mixture Models
• Generative adversarial networks with joint distribution moment matching

Cites work

• Manifold regularization: a geometric framework for learning from labeled and unlabeled examples
• Understanding Estimation and Generalization Error of Generative Adversarial Networks

Cited in

(2)

• scientific article; zbMATH DE number 7306864 (Why is no real title available?)
• Improving the quality of generative models through Smirnov transformation

Describes a project that uses

Uses Software

• Wasserstein GAN
• MMD GAN
• MNIST
• CelebA

This page was built for publication: MR-GAN: Manifold Regularized Generative Adversarial Networks for Scientific Data

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5018897)