Variational Inference for Gaussian Process Modulated Poisson Processes
This work addresses a computational bottleneck for researchers in fields like neuroscience and geo-statistics, offering a significant speed-up over existing methods, though it is an incremental improvement in inference efficiency.
The authors tackled the computational cost of inference for Gaussian-process-modulated Poisson processes by developing the first fully variational Bayesian scheme, which scales linearly with observed events and is orders of magnitude faster than previous methods, as demonstrated on synthetic and real-world datasets like coal mining disasters and Malaria predictions in Kenya.
We present the first fully variational Bayesian inference scheme for continuous Gaussian-process-modulated Poisson processes. Such point processes are used in a variety of domains, including neuroscience, geo-statistics and astronomy, but their use is hindered by the computational cost of existing inference schemes. Our scheme: requires no discretisation of the domain; scales linearly in the number of observed events; and is many orders of magnitude faster than previous sampling based approaches. The resulting algorithm is shown to outperform standard methods on synthetic examples, coal mining disaster data and in the prediction of Malaria incidences in Kenya.