softImpute: Matrix Completion via Iterative Soft-Thresholded SVD

Iterative methods for matrix completion that use nuclear-norm regularization. There are two main approaches.The one approach uses iterative soft-thresholded svds to impute the missing values. The second approach uses alternating least squares. Both have an "EM" flavor, in that at each iteration the matrix is completed with the current estimate. For large matrices there is a special sparse-matrix class named "Incomplete" that efficiently handles all computations. The package includes procedures for centering and scaling rows, columns or both, and for computing low-rank SVDs on large sparse centered matrices (i.e. principal components)

AuthorTrevor Hastie <> and Rahul Mazumder <>
Date of publication2015-04-08 00:42:55
MaintainerTrevor Hastie <>

View on CRAN


\%*\%,ANY,SparseplusLowRank-method Man page
as.matrix,Incomplete-method Man page
as.matrix,SparseplusLowRank-method Man page
biScale Man page
clean.warm.start Man page
coerce,matrix,Incomplete-method Man page
coerce,matrix-method Man page
coerce,sparseMatrix,Incomplete-method Man page
colMeans,SparseplusLowRank-method Man page
colSums,SparseplusLowRank-method Man page
complete Man page
complete,Incomplete-method Man page
complete,matrix-method Man page
deBias Man page
dim,SparseplusLowRank-method Man page
impute Man page
Incomplete Man page
Incomplete-class Man page
lambda0 Man page
lambda0,Incomplete-method Man page
lambda0,sparseMatrix-method Man page
lambda0,SparseplusLowRank-method Man page
\%*\%,Matrix,SparseplusLowRank-method Man page
norm,SparseplusLowRank,character-method Man page
rowMeans,SparseplusLowRank-method Man page
rowSums,SparseplusLowRank-method Man page
simpute.als Man page
simpute.svd Man page
softImpute Man page
softImpute.x.Incomplete Man page
softImpute.x.matrix Man page
\%*\%,SparseplusLowRank,ANY-method Man page
SparseplusLowRank-class Man page
\%*\%,SparseplusLowRank,Matrix-method Man page
splr Man page
Ssimpute.als Man page
Ssimpute.svd Man page
Ssvd.als Man page
svd.als Man page
svd.als,sparseMatrix-method Man page
svd.als,SparseplusLowRank-method Man page

Questions? Problems? Suggestions? or email at

Please suggest features or report bugs with the GitHub issue tracker.

All documentation is copyright its authors; we didn't write any of that.