close Warning: Can't synchronize with repository "(default)" (/var/svn/tolp does not appear to be a Subversion repository.). Look in the Trac log for more information.

Changes between Initial Version and Version 2 of Ticket #757


Ignore:
Timestamp:
Oct 12, 2009, 10:10:53 AM (15 years ago)
Author:
Víctor de Buen Remiro
Comment:

Legend:

Unmodified
Added
Removed
Modified

  • Ticket #757

    • Property Status changed from new to accepted

  • Ticket #757 – Description

    initial v2  
    1 Kernel of BSR can handle with arbitrary covariance matrices but Ascii nor Import API's does it
     1Kernel of BSR can handle with arbitrary covariance matrices but Ascii nor Import API's does it.
     2
     3Internally, they are needed three matrices:
     4 1. [[LatexEquation( \Sigma )]]: Simmetric positive define covariance matrix
     5 1. [[LatexEquation( L )]]: Choleski decomposition of covariance, [[LatexEquation( \Sigma=L\cdot L^{T} )]]
     6 1. [[LatexEquation( L^{-T} )]]: Choleski decomposition of inverse of covariance [[LatexEquation( \Sigma^{-1}=L^{-T}\cdot L^{-1} )]]
     7
     8In real problems it's posible that we have precalculated some of these matrices. So, in order to be efficient, specially for large cases, it could be a good feature to admit at least one of these representations:
     9
     10 1. {{{Cov}}}: When we have only the covariance. For example in prior nodes.
     11 1. {{{CovInv}}} : When we have the inverse of the covariance. For example, when it results from a previous linear regression.
     12 1. {{{CovChol}}} : When we have precalculate the Choleski decomposition
     13 1. {{{CovInvChol}}} : When we have precalculate the Choleski decomposition of inverse of covariance matrix.
     14
     15
     16