I have a NxNxM matrix, which I obtained from running M lasso regressions
using bootstrapped data, with known mean and variance.
Each individual regression (aka, each of the M NxN matrixes) is sparse, and
I can obtain standard deviations for each of the weights that were obtained
multiple times.
What I wanted to know is:
1- Is there a way to efficiently calculate the covariance matrix given this
data which isn't than manually calculating all NxN weights?
If there isn't a way to do 1,
2- When calculating the covariance between two very sparse vectors, does it
make sense to include all (0,0) pairs, or should only pairs containing at
least one non-zero variable be included?
Thank you very much,
Federico
------------------------------------------------------------------------------
LogMeIn Rescue: Anywhere, Anytime Remote support for IT. Free Trial
Remotely access PCs and mobile devices and provide instant support
Improve your efficiency, and focus on delivering more value-add services
Discover what IT Professionals Know. Rescue delivers
http://p.sf.net/sfu/logmein_12329d2d
_______________________________________________
Scikit-learn-general mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
