diff options
Diffstat (limited to 'mllib')
| -rw-r--r-- | mllib/src/main/scala/org/apache/spark/mllib/recommendation/ALS.scala | 10 |
1 files changed, 9 insertions, 1 deletions
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/recommendation/ALS.scala b/mllib/src/main/scala/org/apache/spark/mllib/recommendation/ALS.scala index 89ee07063d..c5f64b1350 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/recommendation/ALS.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/recommendation/ALS.scala @@ -18,6 +18,7 @@ package org.apache.spark.mllib.recommendation import scala.collection.mutable.{ArrayBuffer, BitSet} +import scala.math.{abs, sqrt} import scala.util.Random import scala.util.Sorting @@ -301,7 +302,14 @@ class ALS private (var numBlocks: Int, var rank: Int, var iterations: Int, var l * Make a random factor vector with the given random. */ private def randomFactor(rank: Int, rand: Random): Array[Double] = { - Array.fill(rank)(rand.nextDouble) + // Choose a unit vector uniformly at random from the unit sphere, but from the + // "first quadrant" where all elements are nonnegative. This can be done by choosing + // elements distributed as Normal(0,1) and taking the absolute value, and then normalizing. + // This appears to create factorizations that have a slightly better reconstruction + // (<1%) compared picking elements uniformly at random in [0,1]. + val factor = Array.fill(rank)(abs(rand.nextGaussian())) + val norm = sqrt(factor.map(x => x * x).sum) + factor.map(x => x / norm) } /** |