Athanasios Georgiadis presents two tutorials to the seminar group, introducing recent work in spatial statistics on May 5th, and nonparametric density estimation on May 12th. The abstracts for both sessions are available below.
Seminar 1:Recent progress and open directions in spatial statistics
Abstract: Data’s location plays a decisive role in the extraction of statistical decisions. The field of spatial statistics is devoted to the study of phenomena where such spatial dependence is present. In this seminar we will focus on random fields on the sphere and more general manifolds, talking about our recent developments and highlighting future directions.
Seminar 2:Nonparametric density estimation
Abstract: The distribution of a continuous random variable is completely characterized by its probability density function (=:PDF). The estimation of a PDF is of fundamental importance in many scientific areas. In nonparametric density estimation, we construct estimators for such PDFs enjoying the membership of a large smoothness space (Sobolev, Besov, etc). In the last decade, this problem has been extensively studied on several geometric frameworks, decisively affecting the results. In this seminar we will discuss our recent results on nonparametric density estimation on a broad class of metric spaces and we will present some future directions.
Slides for both seminars, as well as a recent paper ‘Kernel and wavelet density estimators on manifolds and more general metric spaces’, are available below.