Entropic optimal transport: convergence of potentials
From MaRDI portal
Abstract: We study the potential functions that determine the optimal density for -entropically regularized optimal transport, the so-called Schr"odinger potentials, and their convergence to the counterparts in classical optimal transport, the Kantorovich potentials. In the limit of vanishing regularization, strong compactness holds in and cluster points are Kantorovich potentials. In particular, the Schr"odinger potentials converge in to the Kantorovich potentials as soon as the latter are unique. These results are proved for all continuous, integrable cost functions on Polish spaces. In the language of Schr"odinger bridges, the limit corresponds to the small-noise regime.
Recommendations
- Entropic optimal transport: geometry and large deviations
- Stability of Schrödinger potentials and convergence of Sinkhorn's algorithm
- Convergence rate of general entropic optimal transport costs
- Entropic regularization of continuous optimal transport problems
- An optimal transport approach for the Schrödinger bridge problem and convergence of Sinkhorn algorithm
Cites work
- 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
- An automorphism of product measures
- An optimal transport approach for the Schrödinger bridge problem and convergence of Sinkhorn algorithm
- Asymptotic analysis of the exponential penalty trajectory in linear programming
- Barycenters in the Wasserstein space
- Closedness of sum spaces and the generalized Schrödinger problem
- Computational optimal transport. With applications to data sciences
- Convergence of entropic schemes for optimal transport and gradient flows
- Convex duality in nonlinear optimal transport
- Decomposition of Multivariate Functions
- Entropy minimization and Schrödinger processes in infinite dimensions
- Entropy minimization, \(DAD\) problems, and doubly stochastic kernels
- From the Schrödinger problem to the Monge-Kantorovich problem
- scientific article; zbMATH DE number 4080537 (Why is no real title available?)
- I-divergence geometry of probability distributions and minimization problems
- Large deviations techniques and applications.
- Note on the Schrödinger equation and \(I\)-projections
- Optimal Transport
- Second order differentiation formula on \(\mathsf{RCD}^*(K,N)\) spaces
- The Sinkhorn algorithm, parabolic optimal transport and geometric Monge-Ampère equations
Cited in
(50)- About the analogy between optimal transport and minimal entropy
- Domain decomposition for entropy regularized optimal transport
- Regularizing effects of the entropy functional in optimal transport and planning problems
- Entropic optimal transport: geometry and large deviations
- Martingale Schrödinger bridges and optimal semistatic portfolios
- Stability of entropic optimal transport and Schrödinger bridges
- Convergence rate of general entropic optimal transport costs
- Entropy martingale optimal transport and nonlinear pricing-hedging duality
- On the Degeneracy of Optimal Transportation
- scientific article; zbMATH DE number 5292626 (Why is no real title available?)
- Quantitative stability of regularized optimal transport and convergence of Sinkhorn's algorithm
- Convergence of entropic schemes for optimal transport and gradient flows
- Gradient estimates for the Schrödinger potentials: convergence to the Brenier map and quantitative stability
- Entropic Optimal Planning for Path-Dependent Mean Field Games
- Stability of Schrödinger potentials and convergence of Sinkhorn's algorithm
- On the difference between entropic cost and the optimal transport cost
- Limit distributions and sensitivity analysis for empirical entropic optimal transport on countable spaces
- An Improved Central Limit Theorem and Fast Convergence Rates for Entropic Transportation Costs
- A strong duality principle for equivalence couplings and total variation
- Long-time behaviour of entropic interpolations
- Limit theorems for entropic optimal transport maps and Sinkhorn divergence
- On entropy martingale optimal transport theory
- Weak semiconvexity estimates for Schrödinger potentials and logarithmic Sobolev inequality for Schrödinger bridges
- An external dual charge approach to the multimarginal optimal transport with Coulomb cost
- Gromov-Wasserstein distances: entropic regularization, duality and sample complexity
- Stability and sample complexity of divergence regularized optimal transport
- Propagation of chaos for mean field Schrödinger problems
- Statistical inference with regularized optimal transport
- An ordinary differential equation for entropic optimal transport and its linearly constrained variants
- Hilbert's projective metric for functions of bounded growth and exponential convergence of Sinkhorn's algorithm
- Tight stability bounds for entropic Brenier maps
- An Eulerian approach to regularized JKO scheme with low-rank tensor decompositions for Bayesian inversion
- Plug-in estimation of Schrödinger bridges
- Quantitative convergence of quadratically regularized linear programs
- Approximation rates of entropic maps in semidiscrete optimal transport
- Quadratically regularized optimal transport: existence and multiplicity of potentials
- Convergence of the Sinkhorn algorithm when the Schrödinger problem has no solution
- On the uniqueness of Kantorovich potentials
- Characterization of transport optimizers via graphs and applications to Stackelberg-Cournot-Nash equilibria
- On the sample complexity of entropic optimal transport
- A uniform rate of convergence for the entropic potentials in the quadratic euclidean setting
- Langevin diffusion approximation to same marginal Schrödinger bridge
- Hessian stability and convergence rates for entropic and Sinkhorn potentials via semiconcavity
- Entropical K-means for clustering and an alternating algorithm
- Quantitative stability in optimal transport for general power costs
- Large deviations for dynamical Schrödinger problems
- The Riemannian geometry of Sinkhorn divergences
- E-ROBOT: a dimension-free method for robust statistics and machine learning via Schrödinger bridge
- A new clustering strategy for geo-referenced time series based on optimal transport
- Wasserstein mirror gradient flow as the limit of the Sinkhorn algorithm
This page was built for publication: Entropic optimal transport: convergence of potentials
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2089759)
