Add multiclass support to hinge_loss #3451

Closed
arjoly opened this Issue Jul 20, 2014 · 6 comments

Comments

Projects
None yet
4 participants
@arjoly
Member

arjoly commented Jul 20, 2014

The hinge_loss metrics could be improved by adding support multiclass hinge loss. For more information, see wikipedia and the narrative documentation.

This would require to enhance the current code, write tests and modify the documentation accordingly.

@arjoly arjoly added Easy labels Jul 20, 2014

@mblondel

This comment has been minimized.

Show comment Hide comment
@mblondel

mblondel Jul 22, 2014

Member

There are several multiclass variants of the hinge loss. The one in the article you link is the variant by Crammer & Singer. We should either accept a parameter to let the user choose or use one function per variant.

Member

mblondel commented Jul 22, 2014

There are several multiclass variants of the hinge loss. The one in the article you link is the variant by Crammer & Singer. We should either accept a parameter to let the user choose or use one function per variant.

@mblondel

This comment has been minimized.

Show comment Hide comment
@mblondel

mblondel Jul 22, 2014

Member

We can also implement the "one-vs-rest" loss, which is simply to sum the hinge losses of each binary classification problem.

Member

mblondel commented Jul 22, 2014

We can also implement the "one-vs-rest" loss, which is simply to sum the hinge losses of each binary classification problem.

@arjoly

This comment has been minimized.

Show comment Hide comment
@arjoly

arjoly Jul 22, 2014

Member

Thanks @mblondel for the precision.

Member

arjoly commented Jul 22, 2014

Thanks @mblondel for the precision.

@SaurabhJha

This comment has been minimized.

Show comment Hide comment
@SaurabhJha

SaurabhJha Aug 1, 2014

Contributor

I am new to Scikit-learn. I am trying to fix this issue.

Contributor

SaurabhJha commented Aug 1, 2014

I am new to Scikit-learn. I am trying to fix this issue.

@SaurabhJha

This comment has been minimized.

Show comment Hide comment
@SaurabhJha

SaurabhJha Aug 25, 2014

Contributor

Hi, I am reading this paper
http://www.ttic.edu/sigml/symposium2011/papers/Moore+DeNero_Regularization.pdf
in order to understand the notation of multi class hinge loss equation at wikipedia(w subscript y and w subscript t). Can anyone please confirm if w subscript f and l are functional margins? Are they product of w evaulated at some feature and the corresponding product?

Also, is there any way to find w from est?

Contributor

SaurabhJha commented Aug 25, 2014

Hi, I am reading this paper
http://www.ttic.edu/sigml/symposium2011/papers/Moore+DeNero_Regularization.pdf
in order to understand the notation of multi class hinge loss equation at wikipedia(w subscript y and w subscript t). Can anyone please confirm if w subscript f and l are functional margins? Are they product of w evaulated at some feature and the corresponding product?

Also, is there any way to find w from est?

@MechCoder

This comment has been minimized.

Show comment Hide comment
@MechCoder

MechCoder Nov 3, 2014

Member

Fixed by #3607

Member

MechCoder commented Nov 3, 2014

Fixed by #3607

@MechCoder MechCoder closed this Nov 3, 2014

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment