EcoSta 2019: Start Registration
View Submission - EcoSta2019
Title: Maximum composite likelihood estimation for determinantal point processes Authors:  Yasutaka Shimizu - Waseda University (Japan) [presenting]
Abstract: The maximum composite likelihood estimators for stationary and isotropic parametric models of determinantal point processes (DPP) are discussed. Since the conditional marginal distribution of the point processes are given by determinant of positive definite kernels, we have the explicit form of the composite likelihoods for every order. This fact enables us to consider the generalized maximum composite likelihood estimator for every order. We will discuss the asymptotic properties using the limit theorems of DPPs.