On Fri, Feb 15, 2013 at 03:45:03PM +0100, Olivier Grisel wrote:
> Alright for minimizing the RMSE on the training set but on the test
> set the error might be minimized in between kinks as on the on real
> distribution, the kinks location might be slightly off the positions
> found on the training
2013/2/15 Gael Varoquaux :
> On Fri, Feb 15, 2013 at 03:03:58PM +0100, Olivier Grisel wrote:
>> > In my opinion, I am not sure that you want an interpolator that
>> > interpolate the model parameters for specific alphas. You may want to
>> > compute the RMSE at the knots of the path, because I thin
On Fri, Feb 15, 2013 at 03:03:58PM +0100, Olivier Grisel wrote:
> > In my opinion, I am not sure that you want an interpolator that
> > interpolate the model parameters for specific alphas. You may want to
> > compute the RMSE at the knots of the path, because I think that this is
> > where they wi
2013/2/15 Gael Varoquaux :
> On Fri, Feb 15, 2013 at 01:28:43PM +0100, Charles-Pierre Astolfi wrote:
>> Just choose the alpha (from a fixed set) that minimizes the RMSE of
>> the prediction of the last time step (or the last n time steps with
>> exponential decay). Maybe I'm mistaken but there's no
On Fri, Feb 15, 2013 at 02:08:14PM +0100, Olivier Grisel wrote:
> I did not know about that. My previous answer is partially wrong then.
And I didn't expect you to. I know this because I wrote the LassoLarsCV.
This illustrates why I am reticent to add to much to this module: we
need to balance the
2013/2/15 Gael Varoquaux :
> On Fri, Feb 15, 2013 at 01:28:43PM +0100, Charles-Pierre Astolfi wrote:
>> Just choose the alpha (from a fixed set) that minimizes the RMSE of
>> the prediction of the last time step (or the last n time steps with
>> exponential decay). Maybe I'm mistaken but there's no
2013/2/15 Charles-Pierre Astolfi :
> On Fri, Feb 15, 2013 at 12:53 PM, Olivier Grisel
> wrote:
>> How do you evaluate which value of alpha is the best if you don't
>> cross validate in one way or another?
>
> Just choose the alpha (from a fixed set) that minimizes the RMSE of
> the prediction of t
On Fri, Feb 15, 2013 at 01:28:43PM +0100, Charles-Pierre Astolfi wrote:
> Just choose the alpha (from a fixed set) that minimizes the RMSE of
> the prediction of the last time step (or the last n time steps with
> exponential decay). Maybe I'm mistaken but there's no easy way to do
> that with Lass
On Fri, Feb 15, 2013 at 12:53 PM, Olivier Grisel
wrote:
> How do you evaluate which value of alpha is the best if you don't
> cross validate in one way or another?
Just choose the alpha (from a fixed set) that minimizes the RMSE of
the prediction of the last time step (or the last n time steps wi
2013/2/15 Charles-Pierre Astolfi :
> On Fri, Feb 15, 2013 at 11:30 AM, Gael Varoquaux
> wrote:
>> On Fri, Feb 15, 2013 at 11:22:02AM +0100, Charles-Pierre Astolfi wrote:
>>> > However, before we do this, I'd like to understand: what is the usecase
>>> > and the purpose for this function?
>>> Which
Yes that is the method I was using, and its not giving the same results.
I'm going to keep working on getting some sim data.
On Fri, Feb 15, 2013 at 5:01 AM, Andreas Mueller
wrote:
> On 02/15/2013 02:10 AM, David Reed wrote:
>
> Could you link that?
>
>
> http://www.mathworks.de/products/stati
On Fri, Feb 15, 2013 at 11:30 AM, Gael Varoquaux
wrote:
> On Fri, Feb 15, 2013 at 11:22:02AM +0100, Charles-Pierre Astolfi wrote:
>> > However, before we do this, I'd like to understand: what is the usecase
>> > and the purpose for this function?
>> Which? lars_path or lasso_path or my proposition
On Fri, Feb 15, 2013 at 11:22:02AM +0100, Charles-Pierre Astolfi wrote:
> > However, before we do this, I'd like to understand: what is the usecase
> > and the purpose for this function?
> Which? lars_path or lasso_path or my proposition?
> What I propose in an faster and almost (in the sense that
2013/2/15 Charles-Pierre Astolfi :
> On Fri, Feb 15, 2013 at 10:35 AM, Gael Varoquaux
> wrote:
>>> WDYT?
>> I find that lars_path is already a function that is complicated-enough,
>> with a signature difficult to understand, so I'd rather not make it more
>> complex. If there is a need, we can add
On Fri, Feb 15, 2013 at 10:35 AM, Gael Varoquaux
wrote:
>> WDYT?
> I find that lars_path is already a function that is complicated-enough,
> with a signature difficult to understand, so I'd rather not make it more
> complex. If there is a need, we can add a similar function that calls
> lars_path
On 02/15/2013 02:10 AM, David Reed wrote:
Could you link that?
http://www.mathworks.de/products/statistics/examples.html?file=/products/demos/shipping/stats/classdemo.html#3
"The classify function can perform classification using different types
of discriminant analysis. First classify the da
2013/2/15 David Lambert :
>
> On Feb 14, 2013, at 6:52 PM, Lars Buitinck wrote:
>
>> 2013/2/15 :
>>> how about softmax?
>>
>> The model is not intended for probability outputs. A predict_proba is
>> not required; just implement a decision_function instead.
>
> Fair enough, and already done. For
On Fri, Feb 15, 2013 at 10:03:55AM +0100, Olivier Grisel wrote:
> I think it would be better to leave lasso_path as it is and add an
> `alphas` option to lars_path instead that would trigger the
> interpolation between the kinks automatically found by the lars
> algorithm.
> WDYT?
I find that lar
2013/2/15 Charles-Pierre Astolfi :
> That was my idea at first, but I was afraid of breaking things.
> As of today, lasso_path returns a list of ElasticNet and that'd become
> a list of LinearModel and it seemed like I would break
> backward-compatibility.
>
> If that's not an issue, I definitely t
19 matches
Mail list logo
