Limit theorems for entropic optimal transport maps and Sinkhorn divergence
From MaRDI portal
(Redirected from Publication:6200901)
Abstract: We study limit theorems for entropic optimal transport (EOT) maps, dual potentials, and the Sinkhorn divergence. The key technical tool we use is a first and second-order Hadamard differentiability analysis of EOT potentials with respect to the marginal distributions, which may be of independent interest. Given the differentiability results, the functional delta method is used to obtain central limit theorems for empirical EOT potentials and maps. The second-order functional delta method is leveraged to establish the limit distribution of the empirical Sinkhorn divergence under the null. Building on the latter result, we further derive the null limit distribution of the Sinkhorn independence test statistic and characterize the correct order. Since our limit theorems follow from Hadamard differentiability of the relevant maps, as a byproduct, we also obtain bootstrap consistency and asymptotic efficiency of the empirical EOT map, potentials, and Sinkhorn divergence.
Cites work
- \{Euclidean, metric, and Wasserstein\} gradient flows: an overview
- A differential approach to the multi-marginal Schrödinger system
- A formula for the time derivative of the entropic cost and applications
- A Multivariate Faa di Bruno Formula with Applications
- A survey of the Schrödinger problem and some of its connections with optimal transport
- An invitation to statistics in Wasserstein space
- An optimal matching problem
- Asymptotic Statistics
- Asymptotics for semidiscrete entropic optimal transport
- Barycenters in the Wasserstein space
- Bootstrap and permutation tests of independence for point processes
- Bracketing metric entropy rates and empirical central limit theorems for function classes of Besov- and Sobolev-type
- Central limit theorems for entropy-regularized optimal transport on finite spaces and statistical applications
- Convergence of entropic schemes for optimal transport and gradient flows
- Density functional theory and optimal transportation with Coulomb cost
- Empirical regularized optimal transport: statistical theory and applications
- Entropic optimal transport: convergence of potentials
- Entropic optimal transport: geometry and large deviations
- Estimation of Wasserstein distances in the spiked transport model
- From the Schrödinger problem to the Monge-Kantorovich problem
- Hedonic price equilibria, stable matching, and optimal transport: Equivalence, topology, and uniqueness
- scientific article; zbMATH DE number 1057566 (Why is no real title available?)
- scientific article; zbMATH DE number 1909499 (Why is no real title available?)
- scientific article; zbMATH DE number 7370595 (Why is no real title available?)
- scientific article; zbMATH DE number 3099866 (Why is no real title available?)
- Jackknife multiplier bootstrap: finite sample approximations to the \(U\)-process supremum with applications
- Large sample confidence regions based on subsamples under minimal assumptions
- Limit laws for empirical optimal solutions in random linear programs
- Matching for teams
- Minimax estimation of smooth optimal transport maps
- Monge's problem with a quadratic cost by the zero-noise limit of \(h\)-path processes
- Monge-Kantorovich depth, quantiles, ranks and signs
- Multimarginal Optimal Transport Maps for One–dimensional Repulsive Costs
- Multivariate ranks and quantiles using optimal transport: consistency, rates and nonparametric testing
- On concepts of directional differentiability
- On convergence and convolutions of random signed measures
- On the rate of convergence in Wasserstein distance of the empirical measure
- On the scaling of multidimensional matrices
- Optimal transport for applied mathematicians. Calculus of variations, PDEs, and modeling
- Optimal Transportation Problem by Stochastic Optimal Control
- Polar factorization and monotone rearrangement of vector‐valued functions
- Quantitative stability of regularized optimal transport and convergence of Sinkhorn's algorithm
- Regularity of Schrödinger's functional equation and mean field PDEs for h-path processes
- Regularity of Schrödinger's functional equation in the weak topology and moment measures
- Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein distance
- Stability of entropic optimal transport and Schrödinger bridges
- Stability of Schrödinger potentials and convergence of Sinkhorn's algorithm
- Statistical data analysis in the Wasserstein space
- The geometry of optimal transportation
- The Speed of Mean Glivenko-Cantelli Convergence
- Uniform Central Limit Theorems
- Vector quantile regression: an optimal transport approach
- Weak convergence and empirical processes. With applications to statistics
Cited in
(11)- A unifying approach to distributional limits for empirical optimal transport
- Gromov-Wasserstein distances: entropic regularization, duality and sample complexity
- Stability and sample complexity of divergence regularized optimal transport
- Background modeling for double Higgs boson production: density ratios and optimal transport
- Plug-in estimation of Schrödinger bridges
- Approximation rates of entropic maps in semidiscrete optimal transport
- On the sample complexity of entropic optimal transport
- Stability and statistical inference for semidiscrete optimal transport maps
- The functional delta method for deriving asymptotic distributions
- The Riemannian geometry of Sinkhorn divergences
- On the robustness of semi-discrete optimal transport
This page was built for publication: Limit theorems for entropic optimal transport maps and Sinkhorn divergence
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6200901)
