The ml.classification.LogisticRegression document points to the logistic regression in spark.mllib, which says:
We implemented two algorithms to solve logistic regression: mini-batch gradient descent and L-BFGS. We recommend L-BFGS over mini-batch gradient descent for faster convergence.
So in spark.mllib there are LogisticRegressionWithLBFGS and LogisticRegressionWithSGD. Which one is used in ml.classification.LogisticRegression?
答案 0 :(得分:0)
它使用来自微风库的LBFGS算法进行L2正则化,使用OWLQN(LBFGS的扩展)进行L1和弹性网络正则化