ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2309.02413
29
2

Hyperbolic contractivity and the Hilbert metric on probability measures

5 September 2023
Samuel N. Cohen
E. Fausti
ArXivPDFHTML
Abstract

This paper gives a self-contained introduction to the Hilbert projective metric H\mathcal{H}H and its fundamental properties, with a particular focus on the space of probability measures. We start by defining the Hilbert pseudo-metric on convex cones, focusing mainly on dual formulations of H\mathcal{H}H . We show that linear operators on convex cones contract in the distance given by the hyperbolic tangent of H\mathcal{H}H, which in particular implies Birkhoff's classical contraction result for H\mathcal{H}H. Turning to spaces of probability measures, where H\mathcal{H}H is a metric, we analyse the dual formulation of H\mathcal{H}H in the general setting, and explore the geometry of the probability simplex under H\mathcal{H}H in the special case of discrete probability measures. Throughout, we compare H\mathcal{H}H with other distances between probability measures. In particular, we show how convergence in H\mathcal{H}H implies convergence in total variation, ppp-Wasserstein distance, and any fff-divergence. Furthermore, we derive a novel sharp bound for the total variation between two probability measures in terms of their Hilbert distance.

View on arXiv
Comments on this paper