Information geometry is an interdisciplinary field in which statistical models are studied by methods of differential geometry. In the framework of this course the following topics will be addressed: basics of differential geometry, exponential families and other parametric distribution families as Riemannian manifolds, Fisher metric, relative entropies and Bregman divergences, statistical manifolds, and applications of information geometry in machine learning, statistical inference and evolutionary dynamics.
Postgraduate doctoral study programme
Frank Nielsen (2018.), An elementary introduction to information geometry., arXiv:1808.08271
Shun-ichi Amari (2016.), Information Geometry and Its Applications, Springer
Nihat Ay, Jürgen Jost, Hông Vân Lê, Lorenz Schwachhöfer (2017.), Information Geometry, Springer
L1 English Level