Optimal transport for generative models

DOI10.1007/978-3-030-98661-2_105MaRDI QIDQ6606492zbMATH OpenFDO

Authors David Xianfeng Gu, Na Lei, Shing-Tung Yau

Publication date 16 September 2024

zbMATH Keywords

manifold learningoptimal transportconvex geometrygenerative adversarial networksMonge-Ampère equationexplainable deep learning

Mathematics Subject Classification ID

Optimal transportation (49Q22) Artificial neural networks and deep learning (68T07) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Computing methodologies for image processing (68U10) Monge-Ampère equations (35J96)

Recommendations

• Optimal transport for generative models
• A geometric view of optimal transportation and generative model
• The Singularity Set of Optimal Transportation Maps
• The singularity set of optimal transportation maps
• Multi-projection of unequal dimension optimal transport theory for generative adversary networks

Cites work

• A geometric view of optimal transportation and generative model
• Area-preserving mesh parameterization for poly-annulus surfaces based on optimal mass transportation
• Convolutional Wasserstein distances: efficient optimal transportation on geometric domains
• Earth mover's distances on discrete surfaces
• Minimizing Flows for the Monge--Kantorovich Problem
• On a Monge-Ampère equation arising in geometric optics
• On a problem of Monge
• On the design of a reflector antenna
• On the design of a reflector antenna. II
• Polar factorization and monotone rearrangement of vector‐valued functions
• Regularity of potential functions of the optimal transportation problem
• Regularity properties of optimal maps between nonconvex domains in the plane
• Some regularity properties of solutions of Monge Ampère equation
• Surface parameterization based on polar factorization
• The refractor problem in reshaping light beams
• Variational principles for Minkowski type problems, discrete optimal transport, and discrete Monge-Ampère equations

Cited in

(3)

• Optimal 1-Wasserstein distance for WGANs
• Global Sinkhorn autoencoder - optimal transport on the latent representation of the full dataset
• An introduction to deep generative modeling

This page was built for publication: Optimal transport for generative models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6606492)