BART-based inference for Poisson processes
This addresses Poisson intensity estimation for applications like medical imaging, astrophysics, and network traffic analysis, representing an incremental extension of BART to a new statistical context.
The paper tackles the problem of estimating intensity for inhomogeneous Poisson processes, introducing a BART-based scheme that enables full posterior inference in non-parametric regression settings, demonstrating performance through simulation studies on synthetic and real datasets up to five dimensions.
The effectiveness of Bayesian Additive Regression Trees (BART) has been demonstrated in a variety of contexts including non-parametric regression and classification. A BART scheme for estimating the intensity of inhomogeneous Poisson processes is introduced. Poisson intensity estimation is a vital task in various applications including medical imaging, astrophysics and network traffic analysis. The new approach enables full posterior inference of the intensity in a non-parametric regression setting. The performance of the novel scheme is demonstrated through simulation studies on synthetic and real datasets up to five dimensions, and the new scheme is compared with alternative approaches.