commons-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Mikkel Meyer Andersen (JIRA)" <>
Subject [jira] [Commented] (MATH-585) Very slow generation of gamma random variates
Date Tue, 07 Jun 2011 08:47:58 GMT


Mikkel Meyer Andersen commented on MATH-585:

I know that it is indeed important, and I will look into it as soon as time allows me to.
R is GPL, so using their implementation is a no-go. But the help file provides the methods
they have implemented:
‘rgamma’ for ‘shape >= 1’ uses

Ahrens, J. H. and Dieter, U. (1982).  Generating gamma variates by
a modified rejection technique.  _Communications of the ACM_,
*25*, 47-54,

and for ‘0 < shape < 1’ uses

Ahrens, J. H. and Dieter, U. (1974).  Computer methods for
sampling from gamma, beta, Poisson and binomial distributions.
_Computing_, *12*, 223-246.

Again, thanks for reporting this - we'll do our best to improve our implementation.

> Very slow generation of gamma random variates
> ---------------------------------------------
>                 Key: MATH-585
>                 URL:
>             Project: Commons Math
>          Issue Type: Improvement
>    Affects Versions: 2.2, 3.0
>         Environment: All
>            Reporter: Darren Wilkinson
>              Labels: Gamma, Random
>   Original Estimate: 6h
>  Remaining Estimate: 6h
> The current implementation of gamma random variate generation works, but uses an inversion
method. This is well-known to be a bad idea. Usually a carefully constructed rejection procedure
is used. To give an idea of the magnitude of the problem, the Gamma variate generation in
Parallel COLT is roughly 50 times faster than in Commons Math. 

This message is automatically generated by JIRA.
For more information on JIRA, see:

View raw message