Behavior and Convergence of Wasserstein Metric in the Framework of Stable Distributions∗
نویسنده
چکیده
In this paper, we aim to explore the speed of convergence of the Wasserstein distance between stable cumulative distribution functions and their empirical counterparts. The theoretical results are compared with the results provided by simulations. The need to use simulations is explained by the fact that all the theoretical results which relate to the speed of convergence of the Wasserstein Metric in the set-up of stable distributions are asymptotic; therefore, the question of when that theory starts to be valid remains open. The asymptotic results are true only for relatively large numbers of observations exceeding hundreds of thousands. In cases dealing with lower numbers of observations, the speed of convergence turns out to be much slower than we might expect.
منابع مشابه
Central Limit Theorem and convergence to stable laws in Mallows distance
We give a new proof of the classical Central Limit Theorem, in the Mallows (Lr-Wasserstein) distance. Our proof is elementary in the sense that it does not require complex analysis, but rather makes use of a simple subadditive inequality related to this metric. The key is to analyse the case where equality holds. We provide some results concerning rates of convergence. We also consider converge...
متن کاملWasserstein distances for discrete measures and convergence in nonparametric mixture models
We consider Wasserstein distance functionals for comparing between and assessing the convergence of latent discrete measures, which serve as mixing distributions in hierarchical and nonparametric mixture models. We explore the space of discrete probability measures metrized by Wasserstein distances, clarify the relationships between Wasserstein distances of mixing distributions and f -divergenc...
متن کاملMinimax rates of convergence for Wasserstein deconvolution with supersmooth errors in any dimension
The subject of this paper is the estimation of a probability measure on R from data observed with an additive noise, under the Wasserstein metric of order p (with p ≥ 1). We assume that the distribution of the errors is known and belongs to a class of supersmooth distributions, and we give optimal rates of convergence for the Wasserstein metric of order p. In particular, we show how to use the ...
متن کاملPerformance and robustness analysis of stochastic jump linear systems using Wasserstein metric
This paper focuses on the performance and the robustness analysis of stochastic jump linear systems. The realization of the state trajectory under stochastic jump processes becomes random variables, which brings forth the probability distributions for the system state. Therefore, a proper metric is necessary to measure the system performance with respect to stochastic switching. In this perspec...
متن کاملConvergence of Latent Mixing Measures in Finite and Infinite Mixture Models By
This paper studies convergence behavior of latent mixing measures that arise in finite and infinite mixture models, using transportation distances (i.e., Wasserstein metrics). The relationship between Wasserstein distances on the space of mixing measures and f -divergence functionals such as Hellinger and Kullback–Leibler distances on the space of mixture distributions is investigated in detail...
متن کامل