Github user sethah commented on a diff in the pull request: https://github.com/apache/spark/pull/16037#discussion_r91206257 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/optimization/LBFGS.scala --- @@ -241,16 +241,24 @@ object LBFGS extends Logging { val bcW = data.context.broadcast(w) val localGradient = gradient - val (gradientSum, lossSum) = data.treeAggregate((Vectors.zeros(n), 0.0))( - seqOp = (c, v) => (c, v) match { case ((grad, loss), (label, features)) => - val l = localGradient.compute( - features, label, bcW.value, grad) - (grad, loss + l) - }, - combOp = (c1, c2) => (c1, c2) match { case ((grad1, loss1), (grad2, loss2)) => - axpy(1.0, grad2, grad1) - (grad1, loss1 + loss2) - }) + val seqOp = (c: (Vector, Double), v: (Double, Vector)) => + (c, v) match { + case ((grad, loss), (label, features)) => + val denseGrad = grad.toDense + val l = localGradient.compute(features, label, bcW.value, denseGrad) + (denseGrad, loss + l) + } + + val combOp = (c1: (Vector, Double), c2: (Vector, Double)) => + (c1, c2) match { case ((grad1, loss1), (grad2, loss2)) => + val denseGrad1 = grad1.toDense --- End diff -- I am still pretty strongly in favor of adding a test case explicitly for this. Just make an RDD with at least one empty partition, and be sure that LBFGS will run on it.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org