A Smoothed Dual Approach for Variational Wasserstein Problems

DOI10.1137/15M1032600zbMath1335.49076OpenAlexW2133478409MaRDI QIDQ2797783

Gabriel Peyré, Marco Cuturi

Publication date: 31 March 2016

Published in: SIAM Journal on Imaging Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1137/15m1032600

zbMATH Keywords

convex optimizationoptimal transportgradient flowsWasserstein barycenterregularized dual methodvariational Wasserstein problems

Mathematics Subject Classification ID

Convex programming (90C25) Numerical methods involving duality (49M29) Computing methodologies for image processing (68U10) Special problems of linear programming (transportation, multi-index, data envelopment analysis, etc.) (90C08) Variational problems in a geometric measure-theoretic setting (49Q20) Existence theories for optimal control problems involving partial differential equations (49J20) Numerical approximation and computational geometry (primarily algorithms) (65D99)

Related Items (21)

Orlicz space regularization of continuous optimal transport problems ⋮ Stochastic approximation versus sample average approximation for Wasserstein barycenters ⋮ Entropic and Displacement Interpolation: A Computational Approach Using the Hilbert Metric ⋮ Semidual Regularized Optimal Transport ⋮ Optimal transport problems regularized by generic convex functions: a geometric and algorithmic approach ⋮ The GenCol Algorithm for High-Dimensional Optimal Transport: General Formulation and Application to Barycenters and Wasserstein Splines ⋮ Machine learning and optimal transport: some statistical and algorithmic tools ⋮ Decentralized convex optimization on time-varying networks with application to Wasserstein barycenters ⋮ Convex histogram-based joint image segmentation with regularized optimal transport cost ⋮ Information geometry connecting Wasserstein distance and Kullback-Leibler divergence via the entropy-relaxed transportation problem ⋮ Fréchet means and Procrustes analysis in Wasserstein space ⋮ Unnamed Item ⋮ Wasserstein Dictionary Learning: Optimal Transport-Based Unsupervised Nonlinear Dictionary Learning ⋮ Generalized Sinkhorn Iterations for Regularizing Inverse Problems Using Optimal Mass Transport ⋮ Image Labeling Based on Graphical Models Using Wasserstein Messages and Geometric Assignment ⋮ Central limit theorems for entropy-regularized optimal transport on finite spaces and statistical applications ⋮ Asymptotic distribution and convergence rates of stochastic algorithms for entropic optimal transportation between probability measures ⋮ Quadratically regularized optimal transport ⋮ Information geometry ⋮ Minimal Geodesics Along Volume-Preserving Maps, Through Semidiscrete Optimal Transport ⋮ A dual approach for optimal algorithms in distributed optimization over networks

Uses Software

• EMD

Cites Work

• Unnamed Item
• Unnamed Item
• A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
• Tomographic reconstruction from a few views: a multi-marginal optimal transport approach
• A class of Cartesian grid embedded boundary algorithms for incompressible flow with time-varying complex geometries
• The Wasserstein gradient flow of the Fisher information and the quantum drift-diffusion equation
• The earth mover's distance as a metric for image retrieval
• Sliced and Radon Wasserstein barycenters of measures
• THE GEOMETRY OF DISSIPATIVE EVOLUTION EQUATIONS: THE POROUS MEDIUM EQUATION
• Convolutional wasserstein distances
• Non-convex Relaxation of Optimal Transport for Color Transfer Between Images
• Convex Variational Image Restoration with Histogram Priors
• Synthesizing and Mixing Stationary Gaussian Texture Models
• Regularized Regression and Density Estimation based on Optimal Transport
• Barycenters in the Wasserstein Space
• Entropic Approximation of Wasserstein Gradient Flows
• Numerical methods for matching for teams and Wasserstein barycenters
• A Numerical Algorithm forL₂Semi-Discrete Optimal Transport in 3D
• A generalized model for optimal transport of images including dissipation and density modulation
• The Discontinuity Set of Solutions of the TV Denoising Problem and Some Extensions
• The Variational Formulation of the Fokker--Planck Equation
• Imaging with Kantorovich--Rubinstein Discrepancy
• Iterative Bregman Projections for Regularized Transportation Problems
• Learning the parts of objects by non-negative matrix factorization
• Convex analysis and monotone operator theory in Hilbert spaces
• Optimal Transport

This page was built for publication: A Smoothed Dual Approach for Variational Wasserstein Problems