On 11/11/2011 04:04 PM, Gael Varoquaux wrote:
> On Fri, Nov 11, 2011 at 04:00:54PM +0100, Andreas Müller wrote:
>> I just implemented the paper "Random Features for Large-Scale Kernel
>> Machines".
> The Rahimi and Recht one :). It's been on my desktop, waiting for
> implementation for something like a year.
>
Maybe I should have given the authors *cough* well good
you knew the work any way.
>> I was wondering whether this would be interesting for sklearn to
>> include. The technique is pretty easy and it takes about 10-20 lines to
>> implement with a fit / transform interface.
> If you find that it does work/is useful on real problem, yes!
I just started working on it. Atm I can get 3% error on MNIST using 
sklearn's SGD.
I'll try some more datasets.
A computer vision group at my university (Cristian Sminchisescu's group) 
is using
a similar technique, called skewed chi2 kernel, for their segmentation 
algorithms.
They won Pascal VOC this year with it, so I guess it should be some good.

The method only makes sense for dense datasets, I am afraid, so I'll see 
what
I can find.

Cheers,
Andy

------------------------------------------------------------------------------
RSA(R) Conference 2012
Save $700 by Nov 18
Register now
http://p.sf.net/sfu/rsa-sfdev2dev1
_______________________________________________
Scikit-learn-general mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general

Reply via email to