Description Usage Arguments Details Value Author(s) References See Also Examples
this determines the "starting" lambda for a sequence of values for
softImpute
, and all nonzero solutions would require a smaller
value for lambda
.
1 |
x |
An m by n matrix. Large matrices can be in "sparseMatrix" format, as
well as "SparseplusLowRank". The latter arise after centering sparse
matrices, for example with |
The remaining arguments only apply to matrices x
in
"sparseMatrix"
, "Incomplete"
, or "SparseplusLowRank"
format.
lambda |
As in |
maxit |
maximum number of iterations. |
trace.it |
with |
thresh |
convergence threshold, measured as the relative changed in the Frobenius norm between two successive estimates. |
It is the largest singular value for the matrix,
with zeros replacing missing values. It uses svd.als
with
rank=2
.
a single number, the largest singular value
Trevor Hastie, Rahul Mazumder
Maintainer: Trevor Hastie hastie@stanford.edu
Rahul Mazumder, Trevor Hastie and Rob Tibshirani (2010)
Spectral Regularization Algorithms for Learning Large Incomplete
Matrices,
https://web.stanford.edu/~hastie/Papers/mazumder10a.pdf
Journal of Machine Learning Research 11 (2010) 2287-2322
softImpute
,Incomplete
, and svd.als
.
1 2 3 4 5 6 7 8 9 10 11 12 |
Loading required package: Matrix
Loaded softImpute 1.4
[1] 195.53
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.