https://github.com/apache/spark/blob/f5aba657396bd4e2e03dd06491a2d169a99592a7/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala#L191 maxIter is set to max(300, 3 * # singular values). Is there a particular reason for this? And if not, would it be appropriate to submit a PR exposing that parameter? I have not contributed to spark before, so I don’t know if a small api change like that would require a discussion beforehand.
Thanks! Sam
