Convergence rates for empirical barycenters in metric spaces: curvature, convexity and extendable geodesics

@article{AhidarCoutrix2018ConvergenceRF,
  title={Convergence rates for empirical barycenters in metric spaces: curvature, convexity and extendable geodesics},
  author={Adil Ahidar-Coutrix and Thibaut Le Gouic and Q. Paris},
  journal={Probability Theory and Related Fields},
  year={2018},
  volume={177},
  pages={323-368}
}
This paper provides rates of convergence for empirical (generalised) barycenters on compact geodesic metric spaces under general conditions using empirical processes techniques. Our main assumption is termed a variance inequality and provides a strong connection between usual assumptions in the field of empirical processes and central concepts of metric geometry. We study the validity of variance inequalities in spaces of non-positive and non-negative Aleksandrov curvature. In this last… Expand
20 Citations
Online learning with exponential weights in metric spaces
  • Q. Paris
  • Computer Science, Mathematics
  • ArXiv
  • 2021
  • PDF
Convergence Rates for the Generalized Fr\'echet Mean via the Quadruple Inequality
  • 12
  • Highly Influenced
  • PDF
Statistical Inference on the Hilbert Sphere with Application to Random Densities
  • 1
  • PDF
...
1
2
...

References

SHOWING 1-10 OF 68 REFERENCES
Ricci curvature for metric-measure spaces via optimal transport
  • 917
  • Highly Influential
  • PDF
Probability Measures on Metric Spaces of Nonpositive Curvature
  • 219
  • PDF
Barycenters in the Wasserstein Space
  • 441
  • PDF
Existence and consistency of Wasserstein barycenters
  • 83
  • PDF
Barycenters in Alexandrov spaces of curvature bounded below
  • 37
  • PDF
A rigidity theorem in Alexandrov spaces with lower curvature bound
  • 11
  • Highly Influential
  • PDF
LARGE SAMPLE THEORY OF INTRINSIC AND EXTRINSIC SAMPLE MEANS ON MANIFOLDS—II
  • 246
...
1
2
3
4
5
...