Timeline for Best PCA algorithm for huge number of features (>10K)?
Current License: CC BY-SA 2.5
3 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Sep 18, 2010 at 20:26 | comment | added | ars | OK, I see the link now. This is a fairly simple approach, and like Wikipedia mentions, there are advances upon this basic idea. On reflection though, you're going to have to deal with some kind of trade-offs (convergence in this case). I wonder if you're asking the right question here. Are there really no good bindings to linalg libraries for D? | |
| Sep 18, 2010 at 3:26 | comment | added | dsimcha | The Wikipedia algorithm cites this and is equivalent to this for the case of finding one principal component at a time. | |
| Sep 18, 2010 at 3:04 | history | answered | ars | CC BY-SA 2.5 |