Seminarium KMMF "Teoria Dwoistości"

Information geometry studies statistical-probabilistic models equipped with the structure of a differentiable manifold. We can think of such a model as a family of probabilistic distributions with parameters that play the role of coordinates on a manifold. The structure of a statistical manifold is encoded in the function called the divergence that provides the manifold with the metric, the skewness tensor and connections. During the talk I will try to show that all the above structures can be naturally introduced and investigated in the language of Lie groupoids and Lie algebroids. To attend our online seminar, please use the Zoom identificator: https://us02web.zoom.us/j/8145917621?pwd=bVVKend0SHFKNUNyUUQ4cWNRK3laZz09