Empirical Regularized Optimal Transport: Statistical Theory and Applications

DOI10.1137/19M1278788zbMath1483.62055arXiv1810.09880OpenAlexW3033420020MaRDI QIDQ5027034

Carla Tameling, Marcel Klatt, Axel Munk

Publication date: 3 February 2022

Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1810.09880

zbMATH Keywords

bootstrapparametric optimizationsensitivity analysisprotein networkslimit lawSinkhorn divergenceregularized optimal transport

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Asymptotic distribution theory in statistics (62E20) Asymptotic properties of nonparametric inference (62G20) Convex programming (90C25) Approximation methods and heuristics in mathematical programming (90C59) Optimal transportation (49Q22)

Related Items

Multivariate ranks and quantiles using optimal transport: consistency, rates and nonparametric testing, Minimax confidence intervals for the sliced Wasserstein distance, Stochastic approximation versus sample average approximation for Wasserstein barycenters, Randomized Wasserstein Barycenter Computation: Resampling with Statistical Guarantees, Limit laws for empirical optimal solutions in random linear programs, Estimation of Wasserstein distances in the spiked transport model, Scaling positive random matrices: concentration and asymptotic convergence, 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, Uniform confidence band for optimal transport map on one-dimensional data, Limit theorems for entropic optimal transport maps and Sinkhorn divergence, Central limit theorems for entropy-regularized optimal transport on finite spaces and statistical applications, Asymptotic distribution and convergence rates of stochastic algorithms for entropic optimal transportation between probability measures, Minimax estimation of smooth optimal transport maps, Kantorovich-Rubinstein distance and barycenter for finitely supported measures: foundations and algorithms

Uses Software

• R
• EMD
• DOTmark
• Barycenter
• Wasserstein GAN
• otinference

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Limit laws of the empirical Wasserstein distance: Gaussian distributions
• A sparse multiscale algorithm for dense optimal transport
• Long history of the Monge-Kantorovich transportation problem
• Monge-Kantorovich depth, quantiles, ranks and signs
• Introduction to sensitivity and stability analysis in nonlinear programming
• The auction algorithm for the transportation problem
• Linear and nonlinear programming.
• Robust asymptotic statistics
• Asymptotic analysis of the exponential penalty trajectory in linear programming
• Advances in sensitivity analysis and parametric programming
• Mass transportation problems. Vol. 1: Theory. Vol. 2: Applications
• Tests of goodness of fit based on the \(L_2\)-Wasserstein distance
• The earth mover's distance as a metric for image retrieval
• Weak convergence and empirical processes. With applications to statistics
• Inference on functionals under first order degeneracy
• Quadratically regularized optimal transport
• Central limit theorems for entropy-regularized optimal transport on finite spaces and statistical applications
• Empirical optimal transport on countable metric spaces: distributional limits and statistical applications
• On the entropy of couplings
• Central limit theorems for empirical transportation cost in general dimension
• Introduction to empirical processes and semiparametric inference
• Quadratically Regularized Optimal Transport on Graphs
• Nonparametric Validation of Similar Distributions and Assessment of Goodness of Fit
• Asymptotic Statistics
• Bootstrap Sample Size in Nonregular Cases
• Inference for Empirical Wasserstein Distances on Finite Spaces
• The Phylogenetic Kantorovich–Rubinstein Metric for Environmental Sequence Samples
• Wasserstein Dictionary Learning: Optimal Transport-Based Unsupervised Nonlinear Dictionary Learning
• Regularized Discrete Optimal Transport
• Stabilized Sparse Scaling Algorithms for Entropy Regularized Transport Problems
• Spatially Adaptive Colocalization Analysis in Dual-Color Fluorescence Microscopy
• Iterative Bregman Projections for Regularized Transportation Problems
• A Relationship Between Arbitrary Positive Matrices and Doubly Stochastic Matrices
• Analysis of collision effects for turbulent gas–particle flow in a horizontal channel: Part I. Particle transport
• Convex Analysis
• Optimal Transport