Information geometry
22.11.2023, 14:00 - 16:00 Uhr
– Campus Golm, Building 9, Room 2.22 and via Zoom
Institutskolloquium
Lorenz Schwachhöfer (TU Dortmund), Nihat Ay (TU Hamburg)
14:00 Lorenz Schwachhöfer (TU Dortmund)
14:45 Tea and Coffee Break
15:15 Nihat Ay (TU Hamburg)
Lorenz Schwachhöfer (TU Dortmund): Information Geometry in the classical and quantum setting
Abstract:In this talk, we shall give a survey on developments in classical and quantum Information Geometry. We shall give an introduction to the subject, explain the general construction of parametrization of finite (or probability) measures. We shall also present some recent results on the parametrization of quantum models in quantum Information Geometry and their link to Jordan algebras.
Nihat Ay (TU Hamburg): Information Geometry for Data Science
Abstract: In this talk, we first highlight the importance of the geometric perspective when dealing with learning systems. The impact of this perspective has been demonstrated in terms of the natural gradient method, one of the most prominent information-geometric methods within the field of machine learning. After presenting recent results related to this method, the talk concludes with an outline of further information-geometric structures that are particularly important for mathematical data science.
Wenn Sie digital an den Vorträgen teilnehmen möchten, wenden Sie sich bitte an Prof. Paycha, um die Zugangsdaten zu erhalten.