On Sun, Mar 18, 2012 at 12:22 PM, Andreas <[email protected]> wrote:
> On 03/18/2012 05:07 PM, James Bergstra wrote:
>> On Sat, Mar 17, 2012 at 11:55 PM, Mathieu Blondel<[email protected]>  
>> wrote:
>>
>>>> The alpha specified this way could (should?) have the same name and
>>>> interpretation as the l2_regularization coefficient in the
>>>> SGDClassifier.
>>>>
>>> Would you convert alpha into a C internal value or would you patch
>>> libsvm / liblinear to use alpha? I don't understand how the former
>>> would be different from the scale_C option, in practice.
>>>
>> In the implementation, I would convert it to C and call libsvm
>> similarly to how scale_C is working now. The reason that I piped up on
>> the list was purely for code readability. If I read
>>
>> svm = SVC(C=10)
>>
>> it really looks like svm is an SVM model with C=10.  If there's a
>> implicit scale_C=True in the arguments, it's confusing.  This caused
>> my code to have a bug, and I got annoyed.
>>
>> On the other hand if I had read
>>
>> svm = SVC(alpha=1e-3)
>>
>> then I would have wondered "what's alpha?" and gone to look up the
>> docs and learn how alpha is converted to C.
>>
> I see two possible remedies:
> - Having two different possible parameters, as James and I
>   proposed earlier (and which Lars didn't seem to like much),
>   where the user can specify either "C" or "alpha"
>
> - Changing the "scale_C" option back to "False" by default.
>   That means having different parameter names than other
>   linear models and "inconsistent" cross-validation.
>
> Are there any other options?
>

Another minor variation: make a second libsvm wrapper constructor that
only uses alpha, never C.
e.g.: svm = SVCa(1e-3)

------------------------------------------------------------------------------
This SF email is sponsosred by:
Try Windows Azure free for 90 days Click Here 
http://p.sf.net/sfu/sfd2d-msazure
_______________________________________________
Scikit-learn-general mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general

Reply via email to