Mail Archive Search: <+subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*svd\s+for\s+large\s+array\s*$/>

Results:

References: [ +subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*svd\s+for\s+large\s+array\s*$/: 4 ]

Total 4 documents matching your query.

1. svd for large array (score: 1): Author: jsv@stat.ohio-state.edu; Date: Fri, 22 Jul 2005 10:40:16 -0400 (EDT); Dear listers, I'm using Splus 7.0 on a Windows XP with 4Gb memory. I would like to perform an svd on a rectangular array where one dimension is very large (around 30K) and the other is relatively sma; /archives/html/s-news/2005-07/msg00118.html (7,394 bytes)
2. Re: svd for large array (score: 1): Author: Prof Brian Ripley <ripley@stats.ox.ac.uk>; Date: Sat, 23 Jul 2005 17:59:52 +0100 (BST); What do you want from the svd? In a M x N system the left singular vectors form a M x M system, taking up much more space that the 2Gb Windows will allow S-PLUS. By default svd() avoids this by givin; /archives/html/s-news/2005-07/msg00124.html (9,358 bytes)
3. Re: svd for large array (score: 1): Author: jsv@stat.ohio-state.edu; Date: Sat, 23 Jul 2005 18:46:56 -0400 (EDT); Dear Prof. Ripley: Here is what I get Problem in 1:ll: Cannot create - data would have length greater than 536 870911 (.Machine$integer.max/sizeof(integer)) Use traceback() to see the call stack 10:; /archives/html/s-news/2005-07/msg00125.html (11,984 bytes)
4. Re: svd for large array (score: 1): Author: Prof Brian Ripley <ripley@stats.ox.ac.uk>; Date: Sun, 24 Jul 2005 08:07:53 +0100 (BST); That's 100 x 30000, and you mentioned 8000 x 100. If you want N >> M (and that is not at all clear from your original posting), you need to transpose the matrix or modify my algorithm accordingly. De; /archives/html/s-news/2005-07/msg00126.html (12,873 bytes)

Current List: 1 - 4
Page: [1]