CMStatistics 2017: Start Registration
View Submission - CMStatistics
Title: On Finite Exchangeability and Conditional Independence Authors:  Kayvan Sadeghi - University of Cambridge (United Kingdom) [presenting]
Abstract: We study the independence structure of finitely exchangeable distributions over random vectors and random networks. In particular, we provide necessary and sufficient conditions for an exchangeable vector so that its elements are completely independent or completely dependent. We generalize these results and conditions for exchangeable random networks. In this case, the situation turns out to be more complex as will be described in the talk.