[Swarm-Support] Re: Help in poisson distribution and generator

[Russell Standish]

Different seed would be my guess. Correlations between different seed
values should not be significant.


On Mon, May 15, 2006 at 09:02:17PM -0500, Paul Johnson wrote:
> Sorry, I did not read this mail until today.  It was in the Spam catcher.
> 
> Generators are not linked to distributions.  The distributions just need 
> long streams of integers, and they are just as happy with one as another.
> 
> Now, if you are asking "I've used MT19937 (the best one) generator for 
> one random stream, and I need another random stream to draw values from, 
> what should I use next?" then I don't know.  Perhaps you could 
> initialize another MT19937 generator with a different seed.
> 
> Maybe the experts will advise us.
> 
> 
> address@hidden wrote:
> >Hi folks,
> >
> >I saw in user guide of swarm the following table(about default 
> >generators and distributions):
> >
> >     RandomBitDist   uses    C2TAUS1gen
> >BernoulliDist        uses    C2TAUS2gen
> >UniformIntegerDist   uses    TT403gen
> >UniformUnsignedDist  uses    TT775gen
> >...
> >
> >ExponentialDist      uses    C2TAUS3gen
> >GammaDist    uses    PSWBgen
> >
> >
> >
> >I would like to know what is the recommended generator to poissonDist. 
> >Have anyone worked with this issue?
> >Some tips would be great.
> >
> >
> >
> >
> >
> >
> >
> >
> >
> >--- On Tue 04/25, Ed Baskerville < address@hidden > wrote:
> >
> >    *From: *Ed Baskerville [mailto: address@hidden
> >    *To: address@hidden
> >    *Date: *Tue, 25 Apr 2006 02:05:53 -0700
> >    *Subject: *[Swarm-Support] Proposal: Parallel Parameter Sweeps on
> >    Grids
> >
> >    Hello Swarmers,
> >
> >    There has been talk before on this list about harnessing a network--
> >    yes, a grid--of machines to do ABM parameter sweeps in parallel. (I
> >    even built something for Apple's Xgrid a couple years back, only to
> >    have them change the API just as I got distracted by other things.)
> >    After some discussions with Rick Riolo, I'm trying to get going on a
> >    general system for integrating ABM parameter sweeps with modern grid
> >    systems--not just Xgrid, but Sun Grid Engine, etc.
> >
> >    This effort is only going to get off the ground if I can pay my rent
> >    at the same time, so I'm planning to submit a proposal to Google as
> >    part of their Summer of Code, wherein they fund current or (as in my
> >    case) returning students to work on open-source software projects.
> >
> >    In order to put together the best proposal I can, and in order to
> >    jumpstart community involvement, I've posted a draft outline on my
> >    new software development blog in the hopes of getting feedback from
> >    you all:
> >
> >    http://code.edbaskerville.com/2006/04/25/gridsweeper-proposal/
> >
> >    If you have any thoughts about this project, please leave them in the
> >    comments section on the blog post. I hope this will be useful to a
> >    lot of people.
> >
> >    Thanks in advance,
> >    Ed
> >
> >    _______________________________________________
> >    Support mailing list
> >    address@hidden
> >    http://www.swarm.org/mailman/listinfo/support
> >
> >------------------------------------------------------------------------
> >*Join Excite! - http://www.excite.com*
> >The most personalized portal on the Web!
> >------------------------------------------------------------------------
> >
> >_______________________________________________
> >Support mailing list
> >address@hidden
> >http://www.swarm.org/mailman/listinfo/support
> >  
> 
> 
> -- 
> Paul E. Johnson                       email: address@hidden
> Professor, Political Science          http://pj.freefaculty.org
> 1541 Lilac Lane, Rm 504                              
> University of Kansas                  Office: (785) 864-9086
> Lawrence, Kansas 66044-3177           FAX: (785) 864-5700
> 
> _______________________________________________
> Support mailing list
> address@hidden
> http://www.swarm.org/mailman/listinfo/support

-- 
----------------------------------------------------------------------------
A/Prof Russell Standish                  Phone 8308 3119 (mobile)
Mathematics                                    0425 253119 (")
UNSW SYDNEY 2052                         address@hidden             
Australia                                http://parallel.hpc.unsw.edu.au/rks
            International prefix  +612, Interstate prefix 02
----------------------------------------------------------------------------