Corpus ID: 199405372

Fast convergence of empirical barycenters in Alexandrov spaces and the Wasserstein space

  title={Fast convergence of empirical barycenters in Alexandrov spaces and the Wasserstein space},
  author={Thibaut Le Gouic and Q. Paris and P. Rigollet and Austin Stromme},
  • Thibaut Le Gouic, Q. Paris, +1 author Austin Stromme
  • Published 2019
  • Mathematics
  • This work establishes fast rates of convergence for empirical barycenters over a large class of geodesic spaces with curvature bounds in the sense of Alexandrov. More specifically, we show that parametric rates of convergence are achievable under natural conditions that characterize the bi-extendibility of geodesics emanating from a barycenter. These results largely advance the state-of-the-art on the subject both in terms of rates of convergence and the variety of spaces covered. In particular… CONTINUE READING
    9 Citations
    Gradient descent algorithms for Bures-Wasserstein barycenters
    • 17
    • PDF
    The exponentially weighted average forecaster in geodesic spaces of non-positive curvature
    • Q. Paris
    • Mathematics, Computer Science
    • ArXiv
    • 2020
    • 1
    • PDF
    Statistical inference for Bures-Wasserstein barycenters
    • 15
    • PDF
    Estimation of Wasserstein distances in the Spiked Transport Model
    • 19
    • PDF
    Statistical Inference on the Hilbert Sphere with Application to Random Densities
    • PDF
    Jensen's inequality in geodesic spaces with lower bounded curvature
    • PDF
    The price for fairness in a regression framework
    • 2


    Barycenters in the Wasserstein Space
    • 421
    • PDF
    Fast Computation of Wasserstein Barycenters
    • 395
    • PDF
    Convexities of metric spaces
    • 78
    • PDF
    Gradient Flows: In Metric Spaces and in the Space of Probability Measures
    • 2,356
    • PDF