Entropic optimal transport: geometry and large deviations
From MaRDI portal
Publication:2105212
Abstract: We study the convergence of entropically regularized optimal transport to optimal transport. The main result is concerned with the convergence of the associated optimizers and takes the form of a large deviations principle quantifying the local exponential convergence rate as the regularization parameter vanishes. The exact rate function is determined in a general setting and linked to the Kantorovich potential of optimal transport. Our arguments are based on the geometry of the optimizers and inspired by the use of -cyclical monotonicity in classical transport theory. The results can also be phrased in terms of Schr"odinger bridges.
Recommendations
- Entropic optimal transport: convergence of potentials
- Stability of entropic optimal transport and Schrödinger bridges
- Convergence rate of general entropic optimal transport costs
- Convergence of entropic schemes for optimal transport and gradient flows
- Stability of Schrödinger potentials and convergence of Sinkhorn's algorithm
Cites work
- scientific article; zbMATH DE number 4080537 (Why is no real title available?)
- A formula for the time derivative of the entropic cost and applications
- A survey of the Schrödinger problem and some of its connections with optimal transport
- Abstract convex optimal antiderivatives
- Asymptotic analysis of the exponential penalty trajectory in linear programming
- Contingency tables with given marginals
- Convergence of entropic schemes for optimal transport and gradient flows
- Convergence of the iterative proportional fitting procedure
- Convex Analysis
- Decomposition of Multivariate Functions
- Distribution and quantile functions, ranks and signs in dimension \(d\): a measure transportation approach
- Entropic optimal transport: convergence of potentials
- Entropy minimization, \(DAD\) problems, and doubly stochastic kernels
- Existence and uniqueness of monotone measure-preserving maps
- Fine properties of the optimal Skorokhod embedding problem
- From a large-deviations principle to the Wasserstein gradient flow: a new micro-macro passage
- From large deviations to Wasserstein gradient flows in multiple dimensions
- From the Schrödinger problem to the Monge-Kantorovich problem
- I-divergence geometry of probability distributions and minimization problems
- Iterative Bregman projections for regularized transportation problems
- Long-time behaviour of entropic interpolations
- Mass transportation problems. Vol. 1: Theory. Vol. 2: Applications
- Minimization of energy functionals applied to some inverse problems
- Minimizers of energy functionals
- Monge's problem with a quadratic cost by the zero-noise limit of \(h\)-path processes
- Monge-Kantorovich depth, quantiles, ranks and signs
- Multivariate Rank-Based Distribution-Free Nonparametric Testing Using Measure Transportation
- Multivariate ranks and quantiles using optimal transport: consistency, rates and nonparametric testing
- On a problem of optimal transport under marginal martingale constraints
- On the regularity of solutions of optimal transportation problems
- On the relation between optimal transport and Schrödinger bridges: a stochastic control viewpoint
- Optimal Transport
- Optimal control for absolutely continuous stochastic processes and the mass transportation problem
- Optimal entropy-transport problems and a new Hellinger-Kantorovich distance between positive measures
- Optimal transport and Skorokhod embedding
- Regularity of monotone transport maps between unbounded domains
- Regularity of potential functions of the optimal transportation problem
- Second order differentiation formula on \(\mathsf{RCD}^*(K,N)\) spaces
- Stability of entropic optimal transport and Schrödinger bridges
- The Entropic Regularization of the Monge Problem on the Real Line
- The Sinkhorn algorithm, parabolic optimal transport and geometric Monge-Ampère equations
- The geometry of optimal transportation
- The maximal normal operator space and integration of subdifferentials of nonconvex functions
- Wasserstein gradient flows from large deviations of many-particle limits
Cited in
(34)- A unifying approach to distributional limits for empirical optimal transport
- Entropic approximation of \(\infty \)-optimal transport problems
- Stability of Schrödinger potentials and convergence of Sinkhorn's algorithm
- Gradient estimates for the Schrödinger potentials: convergence to the Brenier map and quantitative stability
- Entropical optimal transport, Schrödinger's system and algorithms
- Asymptotics for semidiscrete entropic optimal transport
- Central limit theorems for entropy-regularized optimal transport on finite spaces and statistical applications
- A geometric perspective on regularized optimal transport
- Long-time behaviour of entropic interpolations
- When optimal transport meets information geometry
- Limit theorems for entropic optimal transport maps and Sinkhorn divergence
- On entropy martingale optimal transport theory
- Asymptotic distribution and convergence rates of stochastic algorithms for entropic optimal transportation between probability measures
- Empirical regularized optimal transport: statistical theory and applications
- Feynman-Kac formula under a finite entropy condition
- Convergence of entropic schemes for optimal transport and gradient flows
- Optimal transport and large number of particles
- Quantitative stability of regularized optimal transport and convergence of Sinkhorn's algorithm
- Entropy martingale optimal transport and nonlinear pricing-hedging duality
- Convergence rates for regularized optimal transport via quantization
- scientific article; zbMATH DE number 1665393 (Why is no real title available?)
- Entropic optimal transport: convergence of potentials
- Propagation of chaos for mean field Schrödinger problems
- Entropic regularization of continuous optimal transport problems
- Multiplicative Schrödinger problem and the Dirichlet transport
- Entropic and displacement interpolation: a computational approach using the Hilbert metric
- Quantitative uniform stability of the iterative proportional fitting procedure
- On the difference between entropic cost and the optimal transport cost
- Toric geometry of entropic regularization
- Convergence rate of general entropic optimal transport costs
- An entropic generalization of Caffarelli's contraction theorem via covariance inequalities
- Stability of entropic optimal transport and Schrödinger bridges
- About the analogy between optimal transport and minimal entropy
- Entropic optimal transport is maximum-likelihood deconvolution
This page was built for publication: Entropic optimal transport: geometry and large deviations
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2105212)
