Github user yinxusen commented on a diff in the pull request:
https://github.com/apache/spark/pull/458#discussion_r11833194
--- Diff:
mllib/src/main/scala/org/apache/spark/mllib/regression/Lasso.scala ---
@@ -87,6 +85,49 @@ class LassoWithSGD private (
}
/**
+ * Train a regression model with L1-regularization and L2-regularization
using
+ * Alternating Direction Method of Multiplier (ADMM).
+ * This solves the l1-regularized least squares regression formulation
+ * f(weights) = 1/2 ||A weights-y||^2 + l1RegParam ||weights||_1 +
l2RegParam/2 ||weights||_2^2
+ * Here the data matrix has n rows, and the input RDD holds the set of
rows of A, each with
+ * its corresponding right hand side label y.
+ * See also the documentation for the precise formulation.
+ */
+class LassoWithADMM private (
+ var numPartitions: Int,
+ var numIterations: Int,
+ var l1RegParam: Double,
+ var l2RegParam: Double,
+ var penalty: Double)
+ extends GeneralizedLinearAlgorithm[LassoModel] with Serializable {
+
--- End diff --
A single blank line is good enough. Same below.
---
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.
---
