[jira] [Updated] (SPARK-1503) Implement Nesterov's accelerated first-order method

2019-05-20 Thread Hyukjin Kwon (JIRA)


 [ 
https://issues.apache.org/jira/browse/SPARK-1503?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Hyukjin Kwon updated SPARK-1503:

Labels: bulk-closed  (was: )

> Implement Nesterov's accelerated first-order method
> ---
>
> Key: SPARK-1503
> URL: https://issues.apache.org/jira/browse/SPARK-1503
> Project: Spark
>  Issue Type: New Feature
>  Components: MLlib
>Reporter: Xiangrui Meng
>Assignee: Aaron Staple
>Priority: Major
>  Labels: bulk-closed
> Attachments: linear.png, linear_l1.png, logistic.png, logistic_l2.png
>
>
> Nesterov's accelerated first-order method is a drop-in replacement for 
> steepest descent but it converges much faster. We should implement this 
> method and compare its performance with existing algorithms, including SGD 
> and L-BFGS.
> TFOCS (http://cvxr.com/tfocs/) is a reference implementation of Nesterov's 
> method and its variants on composite objectives.



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

-
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org



[jira] [Updated] (SPARK-1503) Implement Nesterov's accelerated first-order method

2015-03-06 Thread Aaron Staple (JIRA)

 [ 
https://issues.apache.org/jira/browse/SPARK-1503?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Aaron Staple updated SPARK-1503:

Attachment: logistic_l2.png
logistic.png
linear_l1.png
linear.png

Optimization benchmarks, uploaded 2015-03-06.

 Implement Nesterov's accelerated first-order method
 ---

 Key: SPARK-1503
 URL: https://issues.apache.org/jira/browse/SPARK-1503
 Project: Spark
  Issue Type: New Feature
  Components: MLlib
Reporter: Xiangrui Meng
Assignee: Aaron Staple
 Attachments: linear.png, linear_l1.png, logistic.png, logistic_l2.png


 Nesterov's accelerated first-order method is a drop-in replacement for 
 steepest descent but it converges much faster. We should implement this 
 method and compare its performance with existing algorithms, including SGD 
 and L-BFGS.
 TFOCS (http://cvxr.com/tfocs/) is a reference implementation of Nesterov's 
 method and its variants on composite objectives.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

-
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org



[jira] [Updated] (SPARK-1503) Implement Nesterov's accelerated first-order method

2014-10-10 Thread Xiangrui Meng (JIRA)

 [ 
https://issues.apache.org/jira/browse/SPARK-1503?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Xiangrui Meng updated SPARK-1503:
-
Assignee: Aaron Staple  (was: Xiangrui Meng)

 Implement Nesterov's accelerated first-order method
 ---

 Key: SPARK-1503
 URL: https://issues.apache.org/jira/browse/SPARK-1503
 Project: Spark
  Issue Type: New Feature
  Components: MLlib
Reporter: Xiangrui Meng
Assignee: Aaron Staple

 Nesterov's accelerated first-order method is a drop-in replacement for 
 steepest descent but it converges much faster. We should implement this 
 method and compare its performance with existing algorithms, including SGD 
 and L-BFGS.
 TFOCS (http://cvxr.com/tfocs/) is a reference implementation of Nesterov's 
 method and its variants on composite objectives.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

-
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org



[jira] [Updated] (SPARK-1503) Implement Nesterov's accelerated first-order method

2014-09-16 Thread Xiangrui Meng (JIRA)

 [ 
https://issues.apache.org/jira/browse/SPARK-1503?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Xiangrui Meng updated SPARK-1503:
-
Assignee: (was: Xiangrui Meng)

 Implement Nesterov's accelerated first-order method
 ---

 Key: SPARK-1503
 URL: https://issues.apache.org/jira/browse/SPARK-1503
 Project: Spark
  Issue Type: New Feature
  Components: MLlib
Reporter: Xiangrui Meng

 Nesterov's accelerated first-order method is a drop-in replacement for 
 steepest descent but it converges much faster. We should implement this 
 method and compare its performance with existing algorithms, including SGD 
 and L-BFGS.
 TFOCS (http://cvxr.com/tfocs/) is a reference implementation of Nesterov's 
 method and its variants on composite objectives.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

-
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org