[SPARK-11696] MLLIB:Optimization - Extend optimizer output for GradientDescent and LBFGS

• Type: Improvement
• Status: Closed
• Priority: Major
• Resolution: Won't Fix
• Affects Version/s: 1.6.0
• Component/s: ML, MLlib
• Assignee: Unassigned
• Reporter: Narine Kokhlikyan
• Created: 12/Nov/15 16:05
• Updated: 07/Nov/16 18:03
• Resolved: 05/Jan/16 20:03

Description

Hi there,

in current implementation the Optimization:optimize() method returns only the weights for the features.
However, we could make it more transparent and provide more parameters about the optimization, e.g. number of iteration, error, etc.

As discussed in bellow jira, this will be useful:
https://issues.apache.org/jira/browse/SPARK-5575

What do you think ?

Thanks,
Narine

Issue Links

• relates to: SPARK-5256 Improving MLlib optimization APIs
• relates to: SPARK-18303 CLONE - Improving MLlib optimization APIs
• links to: [Github] Pull Request #9667 (NarineK)