Dr Nick Hawes

This list is no longer actively maintained, but I will leave it here for reference. For an up to date list, please see my new site at the University of Oxford.

[jovan18aistats] Ferdian Jovan, Jeremy L. Wyatt and Nick Hawes. Efficient Bayesian Methods for Counting Processes in Partially Observable Environments. In The 21st International Conference on Artificial Intelligence and Statistics (AISTATS 2018). April 2018. [pdf] [bib]
Abstract. When sensors that count events are unreliable, the data sets that result cannot be trusted. We address this common problem by developing practical Bayesian estimators for a partially observable Poisson process (POPP). Unlike Bayesian estimation for a fully observable Poisson process (FOPP) this is non-trivial, since there is no conjugate density for a POPP and the posterior has a number of elements that grow exponentially in the number of observed intervals. We present two tractable approximations, which we combine in a switching filter. This switching filter enables efficient and accurate estimation of the posterior. We perform a detailed empirical analysis, using both simulated and real-world data.
Download:  pdf pdf (2.11 MB)  bib bib
Links: [Google Scholar] [CiteSeer]