Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/3636#discussion_r26540819
--- Diff:
mllib/src/main/scala/org/apache/spark/mllib/optimization/GradientDescent.scala
---
@@ -219,4 +265,39 @@ object GradientDescent extends Logging {
(weights, stochasticLossHistory.toArray)
}
+
+ def runMiniBatchSGD(
+ data: RDD[(Double, Vector)],
+ gradient: Gradient,
+ updater: Updater,
+ stepSize: Double,
+ numIterations: Int,
+ regParam: Double,
+ miniBatchFraction: Double,
+ initialWeights: Vector): (Vector, Array[Double]) =
+ GradientDescent.runMiniBatchSGD(data, gradient, updater, stepSize,
numIterations,
+ regParam, miniBatchFraction,
initialWeights, 0.001)
+
+
+ private def isConverged(previousWeights: Vector, currentWeights: Vector,
+ initialWeights: Vector, convergenceTol: Double):
Boolean = {
+ require(previousWeights != None)
+ require(currentWeights != None)
+ // To compare with convergence tolerance
+ def solutionVecDiff(previousWeight: Vector,
+ currentWeight: Vector): Double = {
+
+ val lastWeight = currentWeight.toBreeze
+ val lastBeforeWeight = previousWeight.toBreeze
+ sum((lastBeforeWeight - lastWeight)
--- End diff --
I'd use a temp value to make sure the vector subtraction is only done once.
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
