Registered Data

[02394] Gaussian distributions on Riemannian symmetric spaces of non-positive curvature

  • Session Time & Room : 5D (Aug.25, 15:30-17:10) @F402
  • Type : Contributed Talk
  • Abstract : Learning from data that live in Riemannian manifolds has become central to many applications, ranging from radar signal processing to neuroscience. In this talk, we present a generalisation of Gaussian distributions to Riemannian symmetric spaces of non-positive curvature, which include hyperbolic spaces, as well as spaces of real, complex and quaternion positive definite matrices, and spaces of structured Toeplitz or block-Toeplitz positive definite matrices and discuss applications to geometric statistics on such spaces.
  • Classification : 53C22, 53B20, 53B50, 53C80, 53C35, Geometric statistics, probability on manifolds
  • Format : Talk at Waseda University
  • Author(s) :
    • Cyrus Mostajeran (Nanyang Technological University)
    • Salem Said (Université Grenoble-Alpes)