Fisher Information Geometry of Beta and Dirichlet Distributions (Dr. Alice Le Brigant)
LOGML Summer School 2022
Talk Title: Fisher Information Geometry of Beta and Dirichlet Distributions
Abstract: The Fisher information metric is a Riemannian metric defined on the parameter space of families of probability distributions. It provides geometric tools that are useful to perform statistics and learning on probability distributions, inside a given parametric family. It is well-known since the 1980s that in the case of normal distributions, Fisher information geometry amounts to hyperbolic geometry. In this talk we will investigate the geometry of Dirichlet distributions, and beta distributions as a particular case. We show that it is negatively curved and geodesically complete. This guarantees the uniqueness of the notion of mean and makes it a suitable geometry to apply learning algorithms such as K-means clustering.
Speaker Bio: Alice Le Brigant is an Assistant Professor in the Applied Mathematics team SAMM at University Paris 1 Pantheon Sorbonne. Previously, she was a Postdoctoral Fellow at the French Civil Aviation School, in collaboration with the Toulouse Mathematics Institute. She obtained her PhD in Applied Mathematics from the University of Bordeaux in 2017. Her research interests are at the interface of statistics and applied Riemannian geometry.
Видео Fisher Information Geometry of Beta and Dirichlet Distributions (Dr. Alice Le Brigant) канала LOGML Summer School
Talk Title: Fisher Information Geometry of Beta and Dirichlet Distributions
Abstract: The Fisher information metric is a Riemannian metric defined on the parameter space of families of probability distributions. It provides geometric tools that are useful to perform statistics and learning on probability distributions, inside a given parametric family. It is well-known since the 1980s that in the case of normal distributions, Fisher information geometry amounts to hyperbolic geometry. In this talk we will investigate the geometry of Dirichlet distributions, and beta distributions as a particular case. We show that it is negatively curved and geodesically complete. This guarantees the uniqueness of the notion of mean and makes it a suitable geometry to apply learning algorithms such as K-means clustering.
Speaker Bio: Alice Le Brigant is an Assistant Professor in the Applied Mathematics team SAMM at University Paris 1 Pantheon Sorbonne. Previously, she was a Postdoctoral Fellow at the French Civil Aviation School, in collaboration with the Toulouse Mathematics Institute. She obtained her PhD in Applied Mathematics from the University of Bordeaux in 2017. Her research interests are at the interface of statistics and applied Riemannian geometry.
Видео Fisher Information Geometry of Beta and Dirichlet Distributions (Dr. Alice Le Brigant) канала LOGML Summer School
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
LOGML 2021: Intro session + Michael Bronstein: Geometric Deep Learning: from Euclid to Drug DesignBack soon!LOGML - Niloy Mitra: Deep 3D Generative ModelingLOGML - Maks Ovsjanikov: Robust learning-based methods for shape correspondenceKeynote: Computational Topology and Applications to Biological Data (Prof. Heather Harrington)LOGML + WiC Tutorial: Getting started on graph MLLOGML - Marinka Zitnik: Graph Representation Learning for Biomedical DiscoveryLOGML - Martin RumpfBack soon!LOGML - Sanja FidlerLOGML 2022 IS COMING!Type-checking Graph Neural Networks (Dr. Petar Veličković)LOGML - Gabriele SteidlTutorial: PyTorch Geometric (Jianxuan You, Rex Ying)Tutorial: Topological Data Analysis (Katherine Benjamin)LOGML - Smita KrishnaswamyFrom Equivariance to Naturality (Dr. Taco Cohen)LOGML - Michael Betancourt: Unravelling A Geometric ConspiracyLOGML - Thomas Kipf: Relational Structure DiscoveryUniverses as Big-Data: Physics, Geometry & AI (Prof. Yang-Hui He)