Re: Stopping criteria for gradient descent

2015-09-29 Thread Yanbo Liang
Hi Nishanth, The diff of solution vectors is compared to relative tolerance or absolute tolerance, you can set convergenceTol which can affect the convergence criteria of SGD. 2015-09-17 8:31 GMT+08:00 Nishanth P S : > Hi, > > I am running LogisticRegressionWithSGD in spark 1.4.1 and it always t

Re: Stopping criteria for gradient descent

2015-09-22 Thread Yanbo Liang
> > Thanks, > Nishanth > > > > -- > View this message in context: > http://apache-spark-user-list.1001560.n3.nabble.com/Stopping-criteria-for-gradient-descent-tp24727.html > Sent from the Apache Spark User List mailing list archive at Nabble.com. > >

Stopping criteria for gradient descent

2015-09-17 Thread nishanthps
http://apache-spark-user-list.1001560.n3.nabble.com/Stopping-criteria-for-gradient-descent-tp24727.html Sent from the Apache Spark User List mailing list archive at Nabble.com. - To unsubscribe, e-mail: user-unsubscr...@spark.apach

Stopping criteria for gradient descent

2015-09-16 Thread Nishanth P S
Hi, I am running LogisticRegressionWithSGD in spark 1.4.1 and it always takes 100 iterations to train (which is the default). It never meets the convergence criteria, shouldn't the convergence criteria for SGD be based on difference in logloss or the difference in accuracy on a held out test set ?