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:

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 WangJianfei wrote: > 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

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: