• Corpus ID: 237572391

Gaussian approximation for penalized Wasserstein barycenters

  title={Gaussian approximation for penalized Wasserstein barycenters},
  author={Nazar Buzun},
  • N. Buzun
  • Published 1 April 2019
  • Mathematics
In this work we consider regularized Wasserstein barycenters (average in Wasserstein distance) in Fourier basis. We prove that random Fourier parameters of the barycenter converge to some Gaussian random vector by distribution. The convergence rate has been derived in finite-sample case with explicit dependence on measures count (n) and the dimension of parameters (p). 

Figures from this paper


Penalization of Barycenters in the Wasserstein Space
A regularization of Wasserstein barycenters for random measures supported on $\mathbb{R}^{d}$ is introduced via convex penalization.
Barycenters in the Wasserstein Space
This paper provides existence, uniqueness, characterizations, and regularity of the barycenter and relates it to the multimarginal optimal transport problem considered by Gangbo and Świech in [Comm. Pure Appl. Math., 51 (1998), pp. 23–45].
Statistical inference for Bures–Wasserstein barycenters
In this work we introduce the concept of Bures-Wasserstein barycenter $Q_*$, that is essentially a Frechet mean of some distribution $\mathbb{P}$ supported on a subspace of positive semi-definite
Wasserstein Barycentric Coordinates: Histogram Regression Using Optimal Transport
This article defines a new way to perform intuitive and geometrically faithful regressions on histogram-valued data. It leverages the theory of optimal transport, and in particular the definition of
Limit laws of the empirical Wasserstein distance: Gaussian distributions
Results are based on the (quadratic) Frechet differentiability of the Wasserstein distance in the gaussian case and extensions to elliptically symmetric distributions are discussed as well as several applications such as bootstrap and statistical testing.
Inference for empirical Wasserstein distances on finite spaces
Summary   The Wasserstein distance is an attractive tool for data analysis but statistical inference is hindered by the lack of distributional limits. To overcome this obstacle, for probability
Large ball probabilities, Gaussian comparison and anti-concentration
We derive tight non-asymptotic bounds for the Kolmogorov distance between the probabilities of two Gaussian elements to hit a ball in a Hilbert space. The key property of these bounds is that they
On the dependence of the Berry–Esseen bound on dimension
Abstract Let X be a random vector with values in R d . Assume that X has mean zero and identity covariance. Write β= E |X| 3 . Let Sn be a normalized sum of n independent copies of X. For Δ n = sup
On the Kantorovich–Rubinstein theorem
Abstract The Kantorovich–Rubinstein theorem provides a formula for the Wasserstein metric W 1 on the space of regular probability Borel measures on a compact metric space. Dudley and de Acosta
On Stein's method for multivariate normal approximation
The purpose of this paper is to synthesize the approaches taken by Chatterjee-Meckes and Reinert-R\"ollin in adapting Stein's method of exchangeable pairs for multivariate normal approximation. The