Gaussian approximation for empirical barycenters

04/01/2019

∙

In this work we consider Wasserstein barycenters (average in Wasserstein distance) in Fourier basis. It includes a provement that a random Fourier parameter of the barycenter is close to a Gaussian random vector by distribution. The convergence rate is O(p/√(n)) depending on measures count (n) and the dimension of parameter (p).

READ FULL TEXT

Gaussian approximation for empirical barycenters

Exact rate of convergence of the mean Wasserstein distance between the empirical and true Gaussian distribution

Wasserstein-1 distance and nonuniform Berry-Esseen bound for a supercritical branching process in a random environment

The Equivalence of Fourier-based and Wasserstein Metrics on Imaging Problems

Rate of convergence of the smoothed empirical Wasserstein distance

Hellinger-Kantorovich barycenter between Dirac measures

Hybrid Wasserstein Distance and Fast Distribution Clustering

Probabilistic learning constrained by realizations using a weak formulation of Fourier transform of probability measures

Gaussian approximation for empirical barycenters

Related Research

Exact rate of convergence of the mean Wasserstein distance between the empirical and true Gaussian distribution

Wasserstein-1 distance and nonuniform Berry-Esseen bound for a supercritical branching process in a random environment

The Equivalence of Fourier-based and Wasserstein Metrics on Imaging Problems

Rate of convergence of the smoothed empirical Wasserstein distance

Hellinger-Kantorovich barycenter between Dirac measures

Hybrid Wasserstein Distance and Fast Distribution Clustering

Probabilistic learning constrained by realizations using a weak formulation of Fourier transform of probability measures