Github user jkbradley commented on a diff in the pull request: https://github.com/apache/spark/pull/3636#discussion_r21724910 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/optimization/GradientDescent.scala --- @@ -182,34 +203,46 @@ object GradientDescent extends Logging { var regVal = updater.compute( weights, Vectors.dense(new Array[Double](weights.size)), 0, 1, regParam)._2 - for (i <- 1 to numIterations) { - val bcWeights = data.context.broadcast(weights) - // Sample a subset (fraction miniBatchFraction) of the total data - // compute and sum up the subgradients on this subset (this is one map-reduce) - val (gradientSum, lossSum, miniBatchSize) = data.sample(false, miniBatchFraction, 42 + i) - .treeAggregate((BDV.zeros[Double](n), 0.0, 0L))( - seqOp = (c, v) => { - // c: (grad, loss, count), v: (label, features) - val l = gradient.compute(v._2, v._1, bcWeights.value, Vectors.fromBreeze(c._1)) - (c._1, c._2 + l, c._3 + 1) - }, - combOp = (c1, c2) => { - // c: (grad, loss, count) - (c1._1 += c2._1, c1._2 + c2._2, c1._3 + c2._3) - }) - - if (miniBatchSize > 0) { - /** - * NOTE(Xinghao): lossSum is computed using the weights from the previous iteration - * and regVal is the regularization value computed in the previous iteration as well. - */ - stochasticLossHistory.append(lossSum / miniBatchSize + regVal) - val update = updater.compute( - weights, Vectors.fromBreeze(gradientSum / miniBatchSize.toDouble), stepSize, i, regParam) - weights = update._1 - regVal = update._2 - } else { - logWarning(s"Iteration ($i/$numIterations). The size of sampled batch is zero") + val b = new Breaks + b.breakable { + for (i <- 1 to numIterations) { + val bcWeights = data.context.broadcast(weights) + // Sample a subset (fraction miniBatchFraction) of the total data + // compute and sum up the subgradients on this subset (this is one map-reduce) + val (gradientSum, lossSum, miniBatchSize) = data.sample(false, miniBatchFraction, 42 + i) + .treeAggregate((BDV.zeros[Double](n), 0.0, 0L))( + seqOp = (c, v) => { + // c: (grad, loss, count), v: (label, features) + val l = gradient.compute(v._2, v._1, bcWeights.value, Vectors.fromBreeze(c._1)) + (c._1, c._2 + l, c._3 + 1) + }, + combOp = (c1, c2) => { + // c: (grad, loss, count) + (c1._1 += c2._1, c1._2 + c2._2, c1._3 + c2._3) + }) + + if (miniBatchSize > 0) { + /** + * NOTE(Xinghao): lossSum is computed using the weights from the previous iteration + * and regVal is the regularization value computed in the previous iteration as well. + */ + stochasticLossHistory.append(lossSum / miniBatchSize + regVal) + val update = updater.compute( --- End diff -- No need to split arguments across multiple lines; I would leave this as it was. It's OK to have a line wrap in the middle of the argument list, if needed to make each line < 100 chars.
--- 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