diff options
author | Reza Zadeh <rizlar@gmail.com> | 2014-01-01 20:02:37 -0800 |
---|---|---|
committer | Reza Zadeh <rizlar@gmail.com> | 2014-01-01 20:02:37 -0800 |
commit | 97dc527849b836703811acdbd6767685585099df (patch) | |
tree | 54a02e2c7c29a962c4a5137c25cc95e16bbf74bd | |
parent | b941b6f7b0131b4382b09740d56916574901fd55 (diff) | |
download | spark-97dc527849b836703811acdbd6767685585099df.tar.gz spark-97dc527849b836703811acdbd6767685585099df.tar.bz2 spark-97dc527849b836703811acdbd6767685585099df.zip |
doc tweak
-rw-r--r-- | docs/mllib-guide.md | 9 |
1 files changed, 5 insertions, 4 deletions
diff --git a/docs/mllib-guide.md b/docs/mllib-guide.md index 08d6d74853..8c490eba69 100644 --- a/docs/mllib-guide.md +++ b/docs/mllib-guide.md @@ -215,17 +215,18 @@ Available algorithms for gradient descent: # Singular Value Decomposition Singular Value Decomposition for Tall and Skinny matrices. -Given an m x n matrix A, this will compute matrices U, S, V such that -A = U * S * V^T +Given an *m x n* matrix *A*, this will compute matrices *U, S, V* such that + +*A = U * S * V^T* 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^TA = V S^2 V^T, +The decomposition is computed by first computing *A^TA = V S^2 V^T*, 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 +as *U = A * V * S^-1* Only singular vectors associated with singular values greater or equal to MIN_SVALUE are recovered. If there are k |