Semidual regularized optimal transport
From MaRDI portal
convex optimizationentropic regularizationgradient flowsoptimal transportSinkhorn algorithmWasserstein barycenter
Existence theories for optimal control problems involving partial differential equations (49J20) Regularity of solutions in optimal control (49N60) Variational problems in a geometric measure-theoretic setting (49Q20) Numerical approximation and computational geometry (primarily algorithms) (65D99) Computing methodologies for image processing (68U10) Convex programming (90C25) Optimal stochastic control (93E20)
Abstract: Variational problems that involve Wasserstein distances and more generally optimal transport (OT) theory are playing an increasingly important role in data sciences. Such problems can be used to form an examplar measure out of various probability measures, as in the Wasserstein barycenter problem, or to carry out parametric inference and density fitting, where the loss is measured in terms of an optimal transport cost to the measure of observations. Despite being conceptually simple, such problems are computationally challenging because they involve minimizing over quantities (Wasserstein distances) that are themselves hard to compute. Entropic regularization has recently emerged as an efficient tool to approximate the solution of such variational Wasserstein problems. In this paper, we give a thorough duality tour of these regularization techniques. In particular, we show how important concepts from classical OT such as c-transforms and semi-discrete approaches translate into similar ideas in a regularized setting. These dual formulations lead to smooth variational problems, which can be solved using smooth, differentiable and convex optimization problems that are simpler to implement and numerically more stable that their un-regularized counterparts. We illustrate the versatility of this approach by applying it to the computation of Wasserstein barycenters and gradient flows of spatial regularization functionals.
Recommendations
- A smoothed dual approach for variational Wasserstein problems
- A smoothed dual approach for variational Wasserstein problems
- Semi-discrete optimal transport: hardness, regularization and numerical solution
- Regularized regression and density estimation based on optimal transport
- Quadratically regularized optimal transport
Cites work
- A class of Cartesian grid embedded boundary algorithms for incompressible flow with time-varying complex geometries
- A fast algorithm for matrix balancing
- A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
- A generalized model for optimal transport of images including dissipation and density modulation
- A numerical algorithm for \(L_2\) semi-discrete optimal transport in 3D
- A Relationship Between Arbitrary Positive Matrices and Doubly Stochastic Matrices
- A smoothed dual approach for variational Wasserstein problems
- A survey of the Schrödinger problem and some of its connections with optimal transport
- Asymptotic analysis of the exponential penalty trajectory in linear programming
- Barycenters in the Wasserstein space
- Clustering with Bregman divergences.
- Convex analysis and monotone operator theory in Hilbert spaces
- Convex variational image restoration with histogram priors
- Convolutional Wasserstein distances: efficient optimal transportation on geometric domains
- Entropic approximation of Wasserstein gradient flows
- scientific article; zbMATH DE number 2107836 (Why is no real title available?)
- Imaging with Kantorovich-Rubinstein discrepancy
- Iterative Bregman projections for regularized transportation problems
- Learning the parts of objects by non-negative matrix factorization
- Minkowski-type theorems and least-squares clustering
- Non-convex relaxation of optimal transport for color transfer between images
- Numerical methods for matching for teams and Wasserstein barycenters
- On the numerical solution of the equation \(\frac{\partial ^ 2z\partial ^ 2z}{\partial x^ 2\partial y^ 2}-(\frac{\partial ^ 2z}{\partial x\partial y})^ 2=f\) and its discretizations. I
- On the scaling of multidimensional matrices
- On the total variation Wasserstein gradient flow and the TV-JKO scheme
- Optimal output-sensitive convex hull algorithms in two and three dimensions
- Optimal Transport
- Optimal transport for applied mathematicians. Calculus of variations, PDEs, and modeling
- Power Diagrams: Properties, Algorithms and Applications
- Regularized barycenters in the Wasserstein space
- Regularized regression and density estimation based on optimal transport
- Robust and scalable Bayes via a median of subset posterior measures
- Sliced and Radon Wasserstein barycenters of measures
- Synthesizing and mixing stationary Gaussian texture models
- The Discontinuity Set of Solutions of the TV Denoising Problem and Some Extensions
- The earth mover's distance as a metric for image retrieval
- THE GEOMETRY OF DISSIPATIVE EVOLUTION EQUATIONS: THE POROUS MEDIUM EQUATION
- The Variational Formulation of the Fokker--Planck Equation
- The Wasserstein gradient flow of the Fisher information and the quantum drift-diffusion equation
- Tomographic reconstruction from a few views: a multi-marginal optimal transport approach
Cited in
(30)- Computations of optimal transport distance with Fisher information regularization
- Quadratically regularized optimal transport
- Domain decomposition for entropy regularized optimal transport
- A multiscale analysis of multi-agent coverage control algorithms
- Positive and free energy satisfying schemes for diffusion with interaction potentials
- Entropic regularization of continuous optimal transport problems
- Optimal transport: discretization and algorithms
- A geometric perspective on regularized optimal transport
- A smoothed dual approach for variational Wasserstein problems
- Regularized regression and density estimation based on optimal transport
- Quadratically regularized optimal transport on graphs
- Regularized optimal transport and the rot mover's distance
- Generalized Sinkhorn iterations for regularizing inverse problems using optimal mass transport
- Fast entropic regularized optimal transport using semidiscrete cost approximation
- Supervised optimal transport
- A smoothed dual approach for variational Wasserstein problems
- Solving large-scale optimization problems with a convergence rate independent of grid size
- Iterative Bregman projections for regularized transportation problems
- Accelerated Bregman Primal-Dual Methods Applied to Optimal Transport and Wasserstein Barycenter Problems
- Semi-discrete optimal transport: hardness, regularization and numerical solution
- A kernel formula for regularized Wasserstein proximal operators
- Regularization for Wasserstein distributionally robust optimization
- The total variation-Wasserstein problem: a new derivation of the Euler-Lagrange equations
- Efficient and exact multimarginal optimal transport with pairwise costs
- Bilevel optimization of the Kantorovich problem and its quadratic regularization. II: Convergence analysis
- Computational optimal transport. With applications to data sciences
- A geometric view of optimal transportation and generative model
- Sparsification techniques for large-scale optimal transport problems
- Fully probabilistic design for optimal transport
- Doubly regularized entropic Wasserstein barycenter
This page was built for publication: Semidual regularized optimal transport
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4554909)
