Thu, 02 Sep 2021

RcppSMC 0.2.4 on CRAN: Even More GSoC !!

A brand new release 0.2.4 of the RcppSMC package arrived on CRAN earlier today, with a dual delay for CRAN closing for a well-earned break, and then being overwhelmed when reopening. Other than that the processing was again versy smooth.

RcppSMC provides Rcpp-based bindings to R for the Sequential Monte Carlo Template Classes (SMCTC) by Adam Johansen described in his JSS article. Sequential Monte Carlo is also referred to as Particle Filter in some contexts.

The package started when I put some Rcpp bindings together based on Adam’s paper and library. It grew when Adam and I supervised Leah South during the 2017 iteration of the Google Summer of Code. And … now it grew again as we have Adam, Leah and myself looking over the shoulders of Ilya Zarubin who did very fine work during the 2021 iteration of the Google Summer of Code that just concluded! So we are now GSoC squared!

This release is effectively all work by Ilya and summarized below.

Changes in RcppSMC version 0.2.4 (2021-09-01)

  • Multiple Sequential Monte Carlo extensions (Ilya Zarubin as part of Google Summer of Code 2021)

    • Provide informative user output (convergence diagnostics) for PMMH example #50 (Ilya in #50 and #52 addressing #25, bullet point 5)

    • Support for tracking of ancestral lines for base sampler class (Ilya in #56)

    • Support for conditional SMC via derived conditionalSampler class (Ilya in #60)

  • Add URL and BugReports to DESCRIPTION (Dirk in #53)

Courtesy of my CRANberries, there is a diffstat report for this release.

More information is on the RcppSMC page. Issues and bugreports should go to the GitHub issue tracker.

If you like this or other open-source work I do, you can now sponsor me at GitHub.

This post by Dirk Eddelbuettel originated on his Thinking inside the box blog. Please report excessive re-aggregation in third-party for-profit settings.

/code/rcpp | permanent link