Stan Math Library

Previous Topic Next Topic
 
classic Classic list List threaded Threaded
5 messages Options
Reply | Threaded
Open this post in threaded view
|

Stan Math Library

Zenna Tavares
Hi everyone

Stan just released a statistical math and auto-diff library.  They suggest their math library is one of the most comprehensive and their autodiff the most performant.  It may be useful as inspiration or to wrap in Julia or both.

https://github.com/stan-dev/math

Zenna

--
You received this message because you are subscribed to the Google Groups "julia-stats" group.
To unsubscribe from this group and stop receiving emails from it, send an email to [hidden email].
For more options, visit https://groups.google.com/d/optout.
Reply | Threaded
Open this post in threaded view
|

Re: Stan Math Library

Kevin Squire

On Wed, Jul 15, 2015 at 3:10 PM, Zenna Tavares <[hidden email]> wrote:
Hi everyone

Stan just released a statistical math and auto-diff library.  They suggest their math library is one of the most comprehensive and their autodiff the most performant.  It may be useful as inspiration or to wrap in Julia or both.


Zenna

--
You received this message because you are subscribed to the Google Groups "julia-stats" group.
To unsubscribe from this group and stop receiving emails from it, send an email to [hidden email].
For more options, visit https://groups.google.com/d/optout.

--
You received this message because you are subscribed to the Google Groups "julia-stats" group.
To unsubscribe from this group and stop receiving emails from it, send an email to [hidden email].
For more options, visit https://groups.google.com/d/optout.
Reply | Threaded
Open this post in threaded view
|

Re: Stan Math Library

John Myles White
In reply to this post by Zenna Tavares
Looks like they might have some numeric stuff we'd want to port over. It's too bad it's all in C++; otherwise it would be a lot easier to just wrap.

 -- John

On Jul 15, 2015, at 3:10 PM, Zenna Tavares <[hidden email]> wrote:

Hi everyone

Stan just released a statistical math and auto-diff library.  They suggest their math library is one of the most comprehensive and their autodiff the most performant.  It may be useful as inspiration or to wrap in Julia or both.


Zenna

--
You received this message because you are subscribed to the Google Groups "julia-stats" group.
To unsubscribe from this group and stop receiving emails from it, send an email to [hidden email].
For more options, visit https://groups.google.com/d/optout.

--
You received this message because you are subscribed to the Google Groups "julia-stats" group.
To unsubscribe from this group and stop receiving emails from it, send an email to [hidden email].
For more options, visit https://groups.google.com/d/optout.
Reply | Threaded
Open this post in threaded view
|

Re: Stan Math Library

Zenna Tavares
I know of Stan.jl.

I think very recently they moved out their math and auto diff routines to a separate package, which is what I was posting about.

Cxx is pretty awesome; could be one approach.

Zenna

On Wednesday, July 15, 2015 at 6:25:48 PM UTC-7, John Myles White wrote:
Looks like they might have some numeric stuff we'd want to port over. It's too bad it's all in C++; otherwise it would be a lot easier to just wrap.

 -- John

On Jul 15, 2015, at 3:10 PM, Zenna Tavares <<a href="javascript:" target="_blank" rel="nofollow" onmousedown="this.href=&#39;javascript:&#39;;return true;" onclick="this.href=&#39;javascript:&#39;;return true;">zennat...@...> wrote:

Hi everyone

Stan just released a statistical math and auto-diff library.  They suggest their math library is one of the most comprehensive and their autodiff the most performant.  It may be useful as inspiration or to wrap in Julia or both.

<a href="https://github.com/stan-dev/math" target="_blank" rel="nofollow" onmousedown="this.href=&#39;https://www.google.com/url?q\75https%3A%2F%2Fgithub.com%2Fstan-dev%2Fmath\46sa\75D\46sntz\0751\46usg\75AFQjCNHGSNCJ4I78oM1VFAOHGQo96d_nrg&#39;;return true;" onclick="this.href=&#39;https://www.google.com/url?q\75https%3A%2F%2Fgithub.com%2Fstan-dev%2Fmath\46sa\75D\46sntz\0751\46usg\75AFQjCNHGSNCJ4I78oM1VFAOHGQo96d_nrg&#39;;return true;">https://github.com/stan-dev/math

Zenna

--
You received this message because you are subscribed to the Google Groups "julia-stats" group.
To unsubscribe from this group and stop receiving emails from it, send an email to <a href="javascript:" target="_blank" rel="nofollow" onmousedown="this.href=&#39;javascript:&#39;;return true;" onclick="this.href=&#39;javascript:&#39;;return true;">julia-stats...@....
For more options, visit <a href="https://groups.google.com/d/optout" target="_blank" rel="nofollow" onmousedown="this.href=&#39;https://groups.google.com/d/optout&#39;;return true;" onclick="this.href=&#39;https://groups.google.com/d/optout&#39;;return true;">https://groups.google.com/d/optout.

--
You received this message because you are subscribed to the Google Groups "julia-stats" group.
To unsubscribe from this group and stop receiving emails from it, send an email to [hidden email].
For more options, visit https://groups.google.com/d/optout.
Reply | Threaded
Open this post in threaded view
|

Re: Stan Math Library

Rob J. Goedman
Hi Zenna,

Yes, this is different from what Stan.jl is attempting to do.

Stan_math_2.7.0 has quite a bit of functionality (it is part of the underpinning of Stan as a PPL) and thus overlaps significantly with Julia itself and many Julia packages. Stan_math_2.7.0 also depends on the Eigen and Boost C++ libraries.

Maybe the challenge is to figure out which parts are useful to Julia users, determine if these can be isolated, and how the performance of those parts (e.g., in terms of speed, robustness, clarity) compare to Julia and native Julia packages like the JuliaStats family, Mamba, Lora, ReverseDiffSource, etc.

Regards,
Rob


On Jul 15, 2015, at 7:29 PM, Zenna Tavares <[hidden email]> wrote:

I know of Stan.jl.

I think very recently they moved out their math and auto diff routines to a separate package, which is what I was posting about.

Cxx is pretty awesome; could be one approach.

Zenna

On Wednesday, July 15, 2015 at 6:25:48 PM UTC-7, John Myles White wrote:
Looks like they might have some numeric stuff we'd want to port over. It's too bad it's all in C++; otherwise it would be a lot easier to just wrap.

 -- John

On Jul 15, 2015, at 3:10 PM, Zenna Tavares <<a href="javascript:" target="_blank" rel="nofollow" onmousedown="this.href='javascript:';return true;" onclick="this.href='javascript:';return true;" class="">zennat...@...> wrote:

Hi everyone

Stan just released a statistical math and auto-diff library.  They suggest their math library is one of the most comprehensive and their autodiff the most performant.  It may be useful as inspiration or to wrap in Julia or both.

<a href="https://github.com/stan-dev/math" target="_blank" rel="nofollow" onmousedown="this.href='https://www.google.com/url?q\75https%3A%2F%2Fgithub.com%2Fstan-dev%2Fmath\46sa\75D\46sntz\0751\46usg\75AFQjCNHGSNCJ4I78oM1VFAOHGQo96d_nrg';return true;" onclick="this.href='https://www.google.com/url?q\75https%3A%2F%2Fgithub.com%2Fstan-dev%2Fmath\46sa\75D\46sntz\0751\46usg\75AFQjCNHGSNCJ4I78oM1VFAOHGQo96d_nrg';return true;" class="">https://github.com/stan-dev/math

Zenna

--
You received this message because you are subscribed to the Google Groups "julia-stats" group.
To unsubscribe from this group and stop receiving emails from it, send an email to <a href="javascript:" target="_blank" rel="nofollow" onmousedown="this.href='javascript:';return true;" onclick="this.href='javascript:';return true;" class="">julia-stats...@....
For more options, visit <a href="https://groups.google.com/d/optout" target="_blank" rel="nofollow" onmousedown="this.href='https://groups.google.com/d/optout';return true;" onclick="this.href='https://groups.google.com/d/optout';return true;" class="">https://groups.google.com/d/optout.


--
You received this message because you are subscribed to the Google Groups "julia-stats" group.
To unsubscribe from this group and stop receiving emails from it, send an email to [hidden email].
For more options, visit https://groups.google.com/d/optout.

--
You received this message because you are subscribed to the Google Groups "julia-stats" group.
To unsubscribe from this group and stop receiving emails from it, send an email to [hidden email].
For more options, visit https://groups.google.com/d/optout.