Timeline for Cholesky decomposition of a large covariance matrix
Current License: CC BY-SA 3.0
7 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jul 17, 2014 at 14:51 | comment | added | David Novotny | Thanks for the clarification by the way ... PCA would be nice, however you still need the covariance matrix to do it and projecting each 59 mil dimensional vector would be pretty slow. | |
| Jul 17, 2014 at 14:49 | comment | added | David Novotny | Of course I am sorry, at first point I thought that L is a vector but since it is an upper triangular matrix, there is no way how to obtain it concerning the fact that the covariance matrix which is two times bigger does not fit into the memory by far (59 milion dimensions) ... | |
| Jul 11, 2014 at 22:55 | comment | added | Robert Israel | ... and the covariance matrix has rank 1 if and only if all the samples are collinear. | |
| Jul 11, 2014 at 21:34 | comment | added | Robert Israel | What $L$ vector? Cholesky decomposition should produce a lower triangular $D \times D$ matrix, not just a vector. The only case where the covariance matrix can be written as $L L'$ where $L$ is a vector is if that covariance matrix has rank 1. | |
| Jul 11, 2014 at 17:55 | comment | added | Alex R. | Can you do some kind of PCA on your matrix? Or at least have a sense as to whether or not it's sparse? | |
| Jul 11, 2014 at 17:32 | review | First posts | |||
| Jul 11, 2014 at 17:36 | |||||
| Jul 11, 2014 at 17:17 | history | asked | David Novotny | CC BY-SA 3.0 |