A complete comparison would take quite a long time and probably warrants a journal paper-length effort. In short:
Anglican: fast, composable queries, parallel, expressive - slower than Stan for models in which one can use HMC and less modular than Venture Stan: no recursion, continuous valued parameters only; good mixing thanks to gradients and HMC Venture: same expressivity; dependency tracking allowing slightly greater diversity of inference techniques albeit at (currently) high overhead, "programmable" inference, On Wednesday, May 13, 2015 at 7:14:38 AM UTC+1, Sunil Nandihalli wrote: > > Hi Frank, > I am looking forward to giving it a shot. I am familiar with and used > Stan. While I understand that stan may not as flexible. A comparison with > of Anglician with Venture and Stan would be very much appreciated. Thanks > for probabilistic-language embedded in clojure. > > Sunil. > > On Wed, May 13, 2015 at 1:16 AM, <hy...@juji-inc.com <javascript:>> wrote: > >> Another question: is there a particular reason why the code of Anglican >> is hosted on BitBucket with read only access for outsider, whereas the >> examples are on Github? Does that mean that you do not anticipate >> contributions to the language from the outside? I saw the license is GPL >> though. >> >> On Tuesday, May 12, 2015 at 3:05:50 AM UTC-7, Frank Wood wrote: >> >>> I'm a professor at Oxford and my group has been working on a new >>> embedded language called Anglican: >>> >>> http://www.robots.ox.ac.uk/~fwood/anglican/ >>> >>> It can be used to do advanced machine learning in Clojure (Java, etc.) >>> applications without having to know anything about inference or math. For >>> example see: >>> >>> http://www.robots.ox.ac.uk/~fwood/anglican/examples/index.html >>> >>> My group would be very interested to get feedback on the language design >>> and its usefulness to the community. Also, frankly, we could use your help >>> in taking it forward, where "help" largely means writing queries and >>> telling us what doesn't work. >>> >> -- >> You received this message because you are subscribed to the Google >> Groups "Clojure" group. >> To post to this group, send email to clo...@googlegroups.com >> <javascript:> >> Note that posts from new members are moderated - please be patient with >> your first post. >> To unsubscribe from this group, send email to >> clojure+u...@googlegroups.com <javascript:> >> For more options, visit this group at >> http://groups.google.com/group/clojure?hl=en >> --- >> You received this message because you are subscribed to the Google Groups >> "Clojure" group. >> To unsubscribe from this group and stop receiving emails from it, send an >> email to clojure+u...@googlegroups.com <javascript:>. >> For more options, visit https://groups.google.com/d/optout. >> > > -- You received this message because you are subscribed to the Google Groups "Clojure" group. To post to this group, send email to clojure@googlegroups.com Note that posts from new members are moderated - please be patient with your first post. To unsubscribe from this group, send email to clojure+unsubscr...@googlegroups.com For more options, visit this group at http://groups.google.com/group/clojure?hl=en --- You received this message because you are subscribed to the Google Groups "Clojure" group. To unsubscribe from this group and stop receiving emails from it, send an email to clojure+unsubscr...@googlegroups.com. For more options, visit https://groups.google.com/d/optout.
