Unify Logistic Regression convergence tolerance of ML & MLlib

mllib/src/main/scala/org/apache/spark/mllib/optimization/LBFGS.scala

@@ -41,7 +41,7 @@ class LBFGS(private var gradient: Gradient, private var updater: Updater)
   extends Optimizer with Logging {
 
   private var numCorrections = 10
-  private var convergenceTol = 1E-4
+  private var convergenceTol = 1E-6
   private var maxNumIterations = 100
   private var regParam = 0.0
 
@@ -59,7 +59,7 @@ class LBFGS(private var gradient: Gradient, private var updater: Updater)
   }
 
   /**
-   * Set the convergence tolerance of iterations for L-BFGS. Default 1E-4.
+   * Set the convergence tolerance of iterations for L-BFGS. Default 1E-6.
    * Smaller value will lead to higher accuracy with the cost of more iterations.
    * This value must be nonnegative. Lower convergence values are less tolerant
    * and therefore generally cause more iterations to be run.

mllib/src/test/scala/org/apache/spark/mllib/classification/LogisticRegressionSuite.scala

@@ -667,9 +667,9 @@ class LogisticRegressionSuite extends SparkFunSuite with MLlibTestSparkContext w
 
   test("binary logistic regression with intercept with L1 regularization") {
     val trainer1 = new LogisticRegressionWithLBFGS().setIntercept(true).setFeatureScaling(true)
-    trainer1.optimizer.setUpdater(new L1Updater).setRegParam(0.12).setConvergenceTol(1E-6)
+    trainer1.optimizer.setUpdater(new L1Updater).setRegParam(0.12)
     val trainer2 = new LogisticRegressionWithLBFGS().setIntercept(true).setFeatureScaling(false)
-    trainer2.optimizer.setUpdater(new L1Updater).setRegParam(0.12).setConvergenceTol(1E-6)
+    trainer2.optimizer.setUpdater(new L1Updater).setRegParam(0.12)
 
     val model1 = trainer1.run(binaryDataset)
     val model2 = trainer2.run(binaryDataset)
@@ -726,9 +726,9 @@ class LogisticRegressionSuite extends SparkFunSuite with MLlibTestSparkContext w
 
   test("binary logistic regression without intercept with L1 regularization") {
     val trainer1 = new LogisticRegressionWithLBFGS().setIntercept(false).setFeatureScaling(true)
-    trainer1.optimizer.setUpdater(new L1Updater).setRegParam(0.12).setConvergenceTol(1E-6)
+    trainer1.optimizer.setUpdater(new L1Updater).setRegParam(0.12)
     val trainer2 = new LogisticRegressionWithLBFGS().setIntercept(false).setFeatureScaling(false)
-    trainer2.optimizer.setUpdater(new L1Updater).setRegParam(0.12).setConvergenceTol(1E-6)
+    trainer2.optimizer.setUpdater(new L1Updater).setRegParam(0.12)
 
     val model1 = trainer1.run(binaryDataset)
     val model2 = trainer2.run(binaryDataset)
@@ -786,9 +786,9 @@ class LogisticRegressionSuite extends SparkFunSuite with MLlibTestSparkContext w
 
   test("binary logistic regression with intercept with L2 regularization") {
     val trainer1 = new LogisticRegressionWithLBFGS().setIntercept(true).setFeatureScaling(true)
-    trainer1.optimizer.setUpdater(new SquaredL2Updater).setRegParam(1.37).setConvergenceTol(1E-6)
+    trainer1.optimizer.setUpdater(new SquaredL2Updater).setRegParam(1.37)
     val trainer2 = new LogisticRegressionWithLBFGS().setIntercept(true).setFeatureScaling(false)
-    trainer2.optimizer.setUpdater(new SquaredL2Updater).setRegParam(1.37).setConvergenceTol(1E-6)
+    trainer2.optimizer.setUpdater(new SquaredL2Updater).setRegParam(1.37)
 
     val model1 = trainer1.run(binaryDataset)
     val model2 = trainer2.run(binaryDataset)
@@ -845,9 +845,9 @@ class LogisticRegressionSuite extends SparkFunSuite with MLlibTestSparkContext w
 
   test("binary logistic regression without intercept with L2 regularization") {
     val trainer1 = new LogisticRegressionWithLBFGS().setIntercept(false).setFeatureScaling(true)
-    trainer1.optimizer.setUpdater(new SquaredL2Updater).setRegParam(1.37).setConvergenceTol(1E-6)
+    trainer1.optimizer.setUpdater(new SquaredL2Updater).setRegParam(1.37)
     val trainer2 = new LogisticRegressionWithLBFGS().setIntercept(false).setFeatureScaling(false)
-    trainer2.optimizer.setUpdater(new SquaredL2Updater).setRegParam(1.37).setConvergenceTol(1E-6)
+    trainer2.optimizer.setUpdater(new SquaredL2Updater).setRegParam(1.37)
 
     val model1 = trainer1.run(binaryDataset)
     val model2 = trainer2.run(binaryDataset)

python/pyspark/mllib/classification.py

@@ -327,7 +327,7 @@ class LogisticRegressionWithLBFGS(object):
     @classmethod
     @since('1.2.0')
     def train(cls, data, iterations=100, initialWeights=None, regParam=0.01, regType="l2",
-              intercept=False, corrections=10, tolerance=1e-4, validateData=True, numClasses=2):
+              intercept=False, corrections=10, tolerance=1e-6, validateData=True, numClasses=2):
         """
         Train a logistic regression model on the given data.
 
@@ -359,7 +359,7 @@ def train(cls, data, iterations=100, initialWeights=None, regParam=0.01, regType
           (default: 10)
         :param tolerance:
           The convergence tolerance of iterations for L-BFGS.
-          (default: 1e-4)
+          (default: 1e-6)
         :param validateData:
           Boolean parameter which indicates if the algorithm should
           validate data before training.