Stability of Schrödinger potentials and convergence of Sinkhorn's algorithm
From MaRDI portal
Abstract: We study the stability of entropically regularized optimal transport with respect to the marginals. Given marginals converging weakly, we establish a strong convergence for the Schr"odinger potentials describing the density of the optimal couplings. When the marginals converge in total variation, the optimal couplings also converge in total variation. This is applied to show that Sinkhorn's algorithm converges in total variation when costs are quadratic and marginals are subgaussian, or more generally for all continuous costs satisfying an integrability condition.
Recommendations
- Quantitative stability of regularized optimal transport and convergence of Sinkhorn's algorithm
- An optimal transport approach for the Schrödinger bridge problem and convergence of Sinkhorn algorithm
- Entropic optimal transport: convergence of potentials
- Stability of entropic optimal transport and Schrödinger bridges
- Entropic optimal transport: geometry and large deviations
Cites work
- A differential approach to the multi-marginal Schrödinger system
- A formula for the time derivative of the entropic cost and applications
- A Relationship Between Arbitrary Positive Matrices and Doubly Stochastic Matrices
- A survey of the Schrödinger problem and some of its connections with optimal transport
- Asymptotic analysis of the exponential penalty trajectory in linear programming
- Concerning nonnegative matrices and doubly stochastic matrices
- Contingency tables with given marginals
- Convergence of the iterative proportional fitting procedure
- Entropic optimal transport: convergence of potentials
- Entropic optimal transport: geometry and large deviations
- From the Schrödinger problem to the Monge-Kantorovich problem
- scientific article; zbMATH DE number 4080537 (Why is no real title available?)
- scientific article; zbMATH DE number 1354815 (Why is no real title available?)
- Monge-Kantorovich depth, quantiles, ranks and signs
- Monge's problem with a quadratic cost by the zero-noise limit of \(h\)-path processes
- On a Least Squares Adjustment of a Sampled Frequency Table When the Expected Marginal Totals are Known
- On the linear convergence of the multimarginal Sinkhorn algorithm
- On the relation between optimal transport and Schrödinger bridges: a stochastic control viewpoint
- On the scaling of multidimensional matrices
- Optimal control for absolutely continuous stochastic processes and the mass transportation problem
- Probability Densities with Given Marginals
- Second order differentiation formula on \(\mathsf{RCD}^*(K,N)\) spaces
- Stability of entropic optimal transport and Schrödinger bridges
- The earth mover's distance as a metric for image retrieval
- The Sinkhorn algorithm, parabolic optimal transport and geometric Monge-Ampère equations
Cited in
(19)- Asymptotic distribution and convergence rates of stochastic algorithms for entropic optimal transportation between probability measures
- Entropic optimal transport: convergence of potentials
- Entropic optimal transport: geometry and large deviations
- Entropical optimal transport, Schrödinger's system and algorithms
- A gradient descent perspective on Sinkhorn
- Quantitative stability of regularized optimal transport and convergence of Sinkhorn's algorithm
- On the linear convergence of the multimarginal Sinkhorn algorithm
- Gradient estimates for the Schrödinger potentials: convergence to the Brenier map and quantitative stability
- The Derivatives of Sinkhorn–Knopp Converge
- An Improved Central Limit Theorem and Fast Convergence Rates for Entropic Transportation Costs
- Limit theorems for entropic optimal transport maps and Sinkhorn divergence
- Weak semiconvexity estimates for Schrödinger potentials and logarithmic Sobolev inequality for Schrödinger bridges
- From optimal transport to discrepancy
- Stability and sample complexity of divergence regularized optimal transport
- Propagation of chaos for mean field Schrödinger problems
- Statistical inference with regularized optimal transport
- Hilbert's projective metric for functions of bounded growth and exponential convergence of Sinkhorn's algorithm
- Tight stability bounds for entropic Brenier maps
- Approximation rates of entropic maps in semidiscrete optimal transport
This page was built for publication: Stability of Schrödinger potentials and convergence of Sinkhorn's algorithm
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6102953)
