An optimal transport approach for the Schrödinger bridge problem and convergence of Sinkhorn algorithm
From MaRDI portal
Publication:2210656
DOI10.1007/s10915-020-01325-7zbMath1478.49043arXiv1911.06850OpenAlexW3093980270MaRDI QIDQ2210656
Augusto Gerolin, Simone Di Marino
Publication date: 7 November 2020
Published in: Journal of Scientific Computing (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1911.06850
Kantorovich dualitySinkhorn algorithmSchrödinger bridge problemiterative proportional fitting procedureentropic regularization of optimal transport
Numerical methods based on necessary conditions (49M05) Methods involving semicontinuity and convergence; relaxation (49J45) Duality theory (optimization) (49N15) Optimal transportation (49Q22)
Related Items
Optimal transportation, modelling and numerical simulation, Orlicz space regularization of continuous optimal transport problems, Time-symmetric optimal stochastic control problems in space-time domains, Quantitative Stability of Regularized Optimal Transport and Convergence of Sinkhorn's Algorithm, Entropical optimal transport, Schrödinger's system and algorithms, Entropy-regularized 2-Wasserstein distance between Gaussian measures, On the Linear Convergence of the Multimarginal Sinkhorn Algorithm, Multi-marginal entropy-transport with repulsive cost, A non-commutative entropic optimal transport approach to quantum composite systems at positive temperature, Entropic regularization of Wasserstein distance between infinite-dimensional Gaussian measures and Gaussian processes, Universal diagonal estimates for minimizers of the Levy-Lieb functional, The dynamical Schrödinger problem in abstract metric spaces, Unbalanced multi-marginal optimal transport, Low-Rank Tensor Approximations for Solving Multimarginal Optimal Transport Problems, Dispersion-constrained martingale Schrödinger problems and the exact joint S\&P 500/VIX smile calibration puzzle, Convergence rate of general entropic optimal transport costs, Stochastic Control Liaisons: Richard Sinkhorn Meets Gaspard Monge on a Schrödinger Bridge, Entropic optimal transport: convergence of potentials, Cortically based optimal transport
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- A survey of the Schrödinger problem and some of its connections with optimal transport
- From the Schrödinger problem to the Monge-Kantorovich problem
- The dual least action problem for an ideal, incompressible fluid
- Conservative diffusions
- Fisher information regularization schemes for Wasserstein gradient flows
- Malliavin calculus and Euclidean quantum mechanics. I: Functional calculus
- Matching for teams
- Hedonic price equilibria, stable matching, and optimal transport: Equivalence, topology, and uniqueness
- On pairs of multidimensional matrices
- On the scaling of multidimensional matrices
- I-divergence geometry of probability distributions and minimization problems
- Minimization of the Kullback information of diffusion processes
- Entropy minimization, \(DAD\) problems, and doubly stochastic kernels
- Second order differentiation formula on \(\mathsf{RCD}(K,N)\) spaces
- Computations of optimal transport distance with Fisher information regularization
- Monge's problem with a quadratic cost by the zero-noise limit of \(h\)-path processes
- Convergence of the iterative proportional fitting procedure
- Multi-marginal entropy-transport with repulsive cost
- An entropic interpolation proof of the HWI inequality
- Benamou-Brenier and duality formulas for the entropic cost on \(\mathsf{RCD}^*(K,N)\) spaces
- Multi-marginal Schrödinger bridges
- Hopf-Cole transformation and Schrödinger problems
- Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein distance
- A large deviation approach to some transportation cost inequalities
- Convolutional wasserstein distances
- Barycenters in the Wasserstein Space
- Scaling algorithms for unbalanced optimal transport problems
- Entropic and Displacement Interpolation: A Computational Approach Using the Hilbert Metric
- The Least Action Principle and the Related Concept of Generalized Flows for Incompressible Perfect Fluids
- Variational processes and stochastic versions of mechanics
- Minimal geodesics on groups of volume-preserving maps and generalized solutions of the Euler equations
- Decomposition of Multivariate Functions
- Optimal maps for the multidimensional Monge-Kantorovich problem
- Generalized Sinkhorn Iterations for Regularizing Inverse Problems Using Optimal Mass Transport
- A Differential Approach to the Multi-Marginal Schrödinger System
- Iterative Bregman Projections for Regularized Transportation Problems
- A Relationship Between Arbitrary Positive Matrices and Doubly Stochastic Matrices
- Estimating Nonnegative Matrices from Marginal Data
- The Speed of Mean Glivenko-Cantelli Convergence
- Convergence of Entropic Schemes for Optimal Transport and Gradient Flows
- The Research Program of Stochastic Deformation (with a View Toward Geometric Mechanics)
- Monotonicity properties of optimal transportation and the FKG and related inequalities