Computational Inference Reading Group Meeting

Discussion Leader: Philip Greengard
Sivaram Ambikasaran, Daniel Foreman-Mackey, Leslie Greengard, David W.
Hogg, Michael O’Neil. 2015.
Fast Direct Methods for Gaussian Processes
https://arxiv.org/abs/1403.6015

The goal of the computational inference reading group is to bring together researchers working in the broad area of statistical computation to help each other understand and dive deeply into topics of mutual interest. Topics include, but are not limited to, Monte Carlo methods, optimization methods, variational methods, variance reduction techniques, reparameterizations, parallel and GPU algorithms, speedups for particular classes of models, etc.

Each meeting will be organized around a focused discussion of a topic based on short assigned reading(s) from papers, book chapters, Git repositories, etc. Each discussion will be led by one or more volunteers whose role is to seed and moderate the discussion among the participants, not to provide an extended lecture.