Geometry, Mechanics and Control Seminar
Statistical geometry - an introduction with examples
Speaker: Katarzyna Grabowska (University of Warsaw, Poland)
Date: Friday, 11 February 2022 - 15:30
Online: us06web.zoom.us/j/7555463367 (ID: 755 546 3367)
Abstract:
The idea of information geometry is to employ tools of differential geometry to analyse the structure of the set of probability distributions relevant to certain statistical or probabilistic problems. The set of probability distributions is given a structure of a statistical manifold i.e. a differential manifold M together with a metric tensor and a skewness tensor or, equivalently, a metric tensor and a pair of dual connections. I will introduce the concept of a statistical manifold, give some examples and indicate the natural groupoid structure behind most of the constructions.
--
修改:vinbo FROM 101.45.158.*
FROM 101.45.158.*