Efficient Bayesian Inference of Sigmoidal Gaussian Cox Processes
This work provides a faster and more flexible inference method for researchers in spatial statistics and machine learning dealing with point process modeling, though it is incremental as it builds on existing variational and sparse GP techniques.
The authors tackled the problem of Bayesian inference for inhomogeneous Poisson processes with Gaussian process intensity via a sigmoid link, developing variational and Laplace approximations that are one order of magnitude faster than exact MCMC and competitive with existing methods, while being more flexible in kernel and domain choices.
We present an approximate Bayesian inference approach for estimating the intensity of an inhomogeneous Poisson process, where the intensity function is modelled using a Gaussian process (GP) prior via a sigmoid link function. Augmenting the model using a latent marked Poisson process and Pólya--Gamma random variables we obtain a representation of the likelihood which is conjugate to the GP prior. We estimate the posterior using a variational free--form mean field optimisation together with the framework of sparse GPs. Furthermore, as alternative approximation we suggest a sparse Laplace's method for the posterior, for which an efficient expectation--maximisation algorithm is derived to find the posterior's mode. Both algorithms compare well against exact inference obtained by a Markov Chain Monte Carlo sampler and standard variational Gauss approach solving the same model, while being one order of magnitude faster. Furthermore, the performance and speed of our method is competitive with that of another recently proposed Poisson process model based on a quadratic link function, while not being limited to GPs with squared exponential kernels and rectangular domains.