Wasserstein proximal of GANs

DOI10.1007/978-3-030-80209-7_57MaRDI QIDQ2117893zbMATH OpenOpenAlexFDO

Authors Wuchen Li, Guido Montúfar, Alex Tong Lin, Stanley Osher

Publication date 22 March 2022

Full work available at URL https://arxiv.org/abs/2102.06862

zbMATH Keywords

generative-adversarial networksnatural gradientWasserstein metric

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Cites work

• Information geometry
• Information geometry and its applications
• Natural gradient via optimal transport
• Ricci curvature for parametric statistics via optimal transport
• Riemannian metrics for neural networks. I: Feedforward networks
• THE GEOMETRY OF DISSIPATIVE EVOLUTION EQUATIONS: THE POROUS MEDIUM EQUATION
• The Variational Formulation of the Fokker--Planck Equation

Cited in

(25)

• Generalized unnormalized optimal transport and its fast algorithms
• Mean-field and kinetic descriptions of neural differential equations
• Computational mean-field information dynamics associated with reaction-diffusion equations
• Some theoretical properties of GANs
• Loss-sensitive generative adversarial networks on Lipschitz densities
• Hessian transport gradient flows
• Neural parametric Fokker-Planck equation
• Interacting Langevin diffusions: gradient structure and ensemble Kalman sampler
• Inferential Wasserstein Generative Adversarial Networks
• A kernel formula for regularized Wasserstein proximal operators
• High order spatial discretization for variational time implicit schemes: Wasserstein gradient flows and reaction-diffusion systems
• Efficient Natural Gradient Descent Methods for Large-Scale PDE-Based Optimization Problems
• Wasserstein information matrix
• Wassmap: Wasserstein Isometric Mapping for Image Manifold Learning
• Fast sinkhorn. II: Collinear triangular matrix and linear time accurate computation of optimal transport
• The Wasserstein metric matrix and its computational property
• Wasserstein Proximal of GANs
• Deep JKO: time-implicit particle methods for general nonlinear gradient flows
• Optimal neural network approximation of Wasserstein gradient direction via convex optimization
• Numerical analysis on neural network projected schemes for approximating one dimensional Wasserstein gradient flows
• On bounds for norms and conditioning of Wasserstein metric matrix
• Parameterized Wasserstein Hamiltonian flow
• Gradient flows and Riemannian structure in the Gromov-Wasserstein geometry
• Wasserstein proximal operators describe score-based generative models and resolve memorization
• Expansive natural neural gradient flows for energy minimization

Describes a project that uses

Uses Software

• Wasserstein GAN

This page was built for publication: Wasserstein proximal of GANs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2117893)