Variational inference for diffusion modulated Cox processes

Prateek Jaiswal, Harsha Honnappa, Vinayak Rao

Keywords: Cox process, variational inference, stochastic differential equation, smoothing posterior density

Abstract: This paper proposes a stochastic variational inference (SVI) method for computing an approximate posterior path measure of a Cox process. These processes are widely used in natural and physical sciences, engineering and operations research, and represent a non-trivial model of a wide array of phenomena. In our work, we model the stochastic intensity as the solution of a diffusion stochastic differential equation (SDE), and our objective is to infer the posterior, or smoothing, measure over the paths given Poisson process realizations. We first derive a system of stochastic partial differential equations (SPDE) for the pathwise smoothing posterior density function, a non-trivial result, since the standard solution of SPDEs typically involves an It\^o stochastic integral, which is not defined pathwise. Next, we propose an SVI approach to approximating the solution of the system. We parametrize the class of approximate smoothing posteriors using a neural network, derive a lower bound on the evidence of the observed point process sample-path, and optimize the lower bound using stochastic gradient descent (SGD). We demonstrate the efficacy of our method on both synthetic and real-world problems, and demonstrate the advantage of the neural network solution over standard numerical solvers.

One-sentence Summary: This paper proposes a variational inference method for computing an approximate smoothing posterior path measure of a Cox process with intensity as a solution to a stochastic differential equation.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=TF1wYrK1l8