Roger Peng: Threadpool package

We're really privileged to have Roger Peng from John Hopkins Bloomberg School of Public Health speak at this meetup. Do come join us to hear about the threadpool package from a world renown educator and statistician.

Abstract:
In this talk I will talk about the threadpool package for R which implements a simple parallel programming backend using a thread pool model that can be dynamically resized during operation. The package builds clusters by setting up a queue of input jobs and having the individual cluster nodes retrieve jobs from the queue one at a time. A few benefits of this model of parallel computing are dynamic resource allocation, automatic load balancing, fault tolerance and restartability. This package will likely be most useful in situations where the jobs being run are embarassingly parallel, and so don't require complex communication between nodes; are relatively long-running, on the order of hours or days; and have individual tasks that are heterogeneous in their runtimes.

Bio:
Roger D. Peng is a Professor of Biostatistics at the Johns Hopkins Bloomberg School of Public Health where his research focuses on the development of statistical methods for addressing environmental health problems. He is also a co-founder of the Johns Hopkins Data Science Specialization, the Simply Statistics blog where he writes about statistics for the general public, the Not So Standard Deviations podcast with Hilary Parker, and The Effort Report podcast with Elizabeth Matsui. He is the recipient of the 2016 Mortimer Spiegelman Award from the American Public Health Association, which honors a statistician who has made outstanding contributions to public health. Roger can be found on Twitter and GitHub at @rdpeng.