incubator-hama-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Edward J. Yoon" <edw...@udanax.org>
Subject Re: [hama-dev] Re: Any matrix decomposition algorithms?
Date Mon, 09 Jun 2008 15:04:38 GMT
> How about the progress on this? Have you started any coding?

No, We should start it

> What do you mean by "high dimensional samples" ?  Big dimension size or a
> lot of dimensions (hypermatrix)?

Hmm, yes. Big dimension size.

Edward

2008/6/10 pi song <pi.songs@gmail.com>:
> I'm already sending to hama-dev@incubator.apache.org
>
> How about the progress on this? Have you started any coding?
> What do you mean by "high dimensional samples" ?  Big dimension size or a
> lot of dimensions (hypermatrix)?
>
> On Mon, Jun 9, 2008 at 11:57 PM, Edward J. Yoon <edward@udanax.org> wrote:
>
>> Hi π,
>>
>> Of course, Eigen decomposition is Hama major problem; It's a central
>> mathematical tool in many pattern recognition and machine learning
>> techniques. Basically, it becomes computationally infeasible in the
>> presence of a large set of high dimensional samples, But we may able
>> to beat it. :-)
>>
>> BTW, Let's move this issue to apache mailing list.
>>
>> Regards, Edward.
>>
>> On Mon, Jun 9, 2008 at 8:20 PM, pi song <pi.songs@gmail.com> wrote:
>> > Dear All,
>> >
>> > Are there any of matrix decomposition algorithms in your roadmap? I'm
>> doing
>> > spectral graph theory and I'm now starting to look at how to parallelize
>> > eigendecomposition. Any of you have explored it before? A few pointers
>> would
>> > be good.  I want to work with you and contribute to Hama.
>> >
>> > Pi
>> >
>>
>> --
>> Best regards,
>> Edward J. Yoon,
>> http://blog.udanax.org
>>
>



-- 
Best regards,
Edward J. Yoon,
http://blog.udanax.org
Mime
View raw message