Fisher-Rao geometry of Dirichlet distributions
نویسندگان
چکیده
In this paper, we study the geometry induced by Fisher-Rao metric on parameter space of Dirichlet distributions. We show that is geodesically complete and has everywhere negative sectional curvature. An important consequence curvature for applications Fr{\'e}chet mean a set distributions uniquely defined in geometry.
منابع مشابه
Fisher-Rao Metric, Geometry, and Complexity of Neural Networks
Abstract. We study the relationship between geometry and capacity measures for deep neural networks from an invariance viewpoint. We introduce a new notion of capacity — the Fisher-Rao norm — that possesses desirable invariance properties and is motivated by Information Geometry. We discover an analytical characterization of the new capacity measure, through which we establish norm-comparison i...
متن کاملGradient Flows in Filtering and Fisher-Rao Geometry
Uncertainty propagation and filtering can be interpreted as gradient flows with respect to suitable metrics in the infinite dimensional manifold of probability density functions. Such a viewpoint has been put forth in recent literature, and a systematic way to formulate and solve the same for linear Gaussian systems has appeared in our previous work where the gradient flows were realized via pr...
متن کاملThe Wasserstein-Fisher-Rao metric
This note gives a summary of the presentation that I gave at the workshop on shape analysis. Based on [CSPV15, CPSV15], we present a generalization of optimal transport to measures that have different total masses. This generalization enjoys most of the properties of standard optimal transport but we will focus on the geometric formulation of the model. We expect this new metric to have interes...
متن کاملOn generalized Cramér-Rao inequalities, generalized Fisher informations and characterizations of generalized q-Gaussian distributions
This paper deals with Cramér-Rao inequalities in the context of nonextensive statistics and in estimation theory. It gives characterizations of generalized q-Gaussian distributions, and introduces generalized versions of Fisher information. The contributions of this paper are (i) the derivation of new extended Cramér-Rao inequalities for the estimation of a parameter, involving general q-moment...
متن کاملOn bounds for the Fisher-Rao distance between multivariate normal distributions
Information geometry is approached here by considering the statistical model of multivariate normal distributions M as a Riemannian manifold with the natural metric provided by the Fisher information matrix. This differential geometric approach to probability theory, introduced by C. Rao in 1945, have been recently applied to different domains such as statistical inference, mathematical program...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Differential Geometry and Its Applications
سال: 2021
ISSN: ['1872-6984', '0926-2245']
DOI: https://doi.org/10.1016/j.difgeo.2020.101702