From 983d6a9c48b69c5f0542922aa8b133f69eb1034d Mon Sep 17 00:00:00 2001 From: Reza Zadeh Date: Mon, 15 Sep 2014 17:41:15 -0700 Subject: [PATCH] [MLlib] Update SVD documentation in IndexedRowMatrix Updating this to reflect the newest SVD via ARPACK Author: Reza Zadeh Closes #2389 from rezazadeh/irmdocs and squashes the following commits: 7fa1313 [Reza Zadeh] Update svd docs 715da25 [Reza Zadeh] Updated computeSVD documentation IndexedRowMatrix --- .../mllib/linalg/distributed/IndexedRowMatrix.scala | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) diff --git a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/IndexedRowMatrix.scala b/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/IndexedRowMatrix.scala index ac6eaea3f4..5c1acca0ec 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/IndexedRowMatrix.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/IndexedRowMatrix.scala @@ -76,16 +76,12 @@ class IndexedRowMatrix( } /** - * Computes the singular value decomposition of this matrix. + * Computes the singular value decomposition of this IndexedRowMatrix. * Denote this matrix by A (m x n), this will compute matrices U, S, V such that A = U * S * V'. * - * There is no restriction on m, but we require `n^2` doubles to fit in memory. - * Further, n should be less than m. - - * The decomposition is computed by first computing A'A = V S^2 V', - * computing svd locally on that (since n x n is small), from which we recover S and V. - * Then we compute U via easy matrix multiplication as U = A * (V * S^-1). - * Note that this approach requires `O(n^3)` time on the master node. + * The cost and implementation of this method is identical to that in + * [[org.apache.spark.mllib.linalg.distributed.RowMatrix]] + * With the addition of indices. * * At most k largest non-zero singular values and associated vectors are returned. * If there are k such values, then the dimensions of the return will be: