Re: Why don't we imp some adaptive learning rate methods, such as adadelat, adam?
Hi, There is a plan to add this into Spark ML. Please check out https://issues.apache.org/jira/browse/SPARK-18023. You can also follow this jira to get the latest update. - Liang-Chi Hsieh | @viirya Spark Technology Center http://www.spark.tc/ -- View this message in context: http://apache-spark-developers-list.1001551.n3.nabble.com/Why-don-t-we-imp-some-adaptive-learning-rate-methods-such-as-adadelat-adam-tp20057p20205.html Sent from the Apache Spark Developers List mailing list archive at Nabble.com. - To unsubscribe e-mail: dev-unsubscr...@spark.apache.org
Re: Why don't we imp some adaptive learning rate methods, such as adadelat, adam?
check out https://github.com/VinceShieh/Spark-AdaOptimizer On Wed, 30 Nov 2016 at 10:52 WangJianfeiwrote: > Hi devs: > Normally, the adaptive learning rate methods can have a fast > convergence > then standard SGD, so why don't we imp them? > see the link for more details > http://sebastianruder.com/optimizing-gradient-descent/index.html#adadelta > > > > -- > View this message in context: > http://apache-spark-developers-list.1001551.n3.nabble.com/Why-don-t-we-imp-some-adaptive-learning-rate-methods-such-as-adadelat-adam-tp20057.html > Sent from the Apache Spark Developers List mailing list archive at > Nabble.com. > > - > To unsubscribe e-mail: dev-unsubscr...@spark.apache.org > >
Why don't we imp some adaptive learning rate methods, such as adadelat, adam?
Hi devs: Normally, the adaptive learning rate methods can have a fast convergence then standard SGD, so why don't we imp them? see the link for more details http://sebastianruder.com/optimizing-gradient-descent/index.html#adadelta -- View this message in context: http://apache-spark-developers-list.1001551.n3.nabble.com/Why-don-t-we-imp-some-adaptive-learning-rate-methods-such-as-adadelat-adam-tp20057.html Sent from the Apache Spark Developers List mailing list archive at Nabble.com. - To unsubscribe e-mail: dev-unsubscr...@spark.apache.org