Computing Bayes: Bayesian Computation from 1763 to the 21st Century
Last night, Gael Martin, David Frazier (from Monash U) and myself arXived a survey on the history of Bayesian computations. This project started when Gael presented a historical overview of Bayesian computation, then entitled ‘Computing Bayes: Bayesian Computation from 1763 to 2017!’, at ‘Bayes on the Beach’ (Queensland, November, 2017). She then decided to build a survey from the material she had gathered, with her usual dedication and stamina. Asking David and I to join forces and bring additional perspectives on this history. While this is a short and hence necessary incomplete history (of not everything!), it hopefully brings some different threads together in an original enough fashion (as I think there is little overlap with recent surveys I wrote). We welcome comments about aspects we missed, skipped or misrepresented, most obviously!
Xi'an's Og 
April 16, 2020 at 8:36 am
Perhaps this is a good opportunity to start referring to the seminal algorithm from 1953 using something other than “the Metropolis algorithm”. According to Marshall Rosenbluth, Nicholas Metropolis gave no contribution to the method. Metropolis was the head of the lab, as recalled by Rosenbluth in a 2003 interview, and “we never had a single scientific discussion with him” (interview at https://tinyurl.com/ycphj24e). Of course in pratice everyone will keep calling it “Metropolis algorithm”, but this seems to be the right venue to make a point, and attempt at giving more spotlight to the other authors. Perhaps “MEROTE”? (MEtropolis, ROsenbluth, TEller). Pretty ugly I know ;)
Another interesting account is at https://tinyurl.com/y9pq5zrf
December 9, 2020 at 12:05 pm
Thank you Umberto! I presume it is indeed difficult to hope for a different naming, but we stressed the role of the Rosenbluths in the paper (see, e.g., footnote ⁶).