[ https://issues.apache.org/jira/browse/SPARK2426?page=com.atlassian.jira.plugin.system.issuetabpanels:commenttabpanel&focusedCommentId=14377357#comment14377357
]
Debasish Das edited comment on SPARK2426 at 3/24/15 6:11 AM:

[~acopich] From your comment before "Anyway, l2 regularized stochastic matrix decomposition
problem is defined as follows
Minimize w.r.t. W and H : R  W*H + \lambda(W + H)
under nonnegativeness and normalization constraints.
.", could you please point me to a good reference with application to collaborative filtering/topic
modeling ? Stochastic matrix decomposition is what we can do in this PR now https://github.com/apache/spark/pull/3221....
For MAP loss, I will open up a PR in a week through JIRA https://issues.apache.org/jira/browse/SPARK6323...I
am very curious how much slower we get compared to stochastic matrix decomposition using ALS
was (Author: debasish83):
[~acopich] From your comment before "Anyway, l2 regularized stochastic matrix decomposition
problem is defined as follows
Minimize w.r.t. W and H : R  W*H + \lambda(W + H)
under nonnegativeness and normalization constraints.
 .  stands for Frobenius norm (or l1).", could you please point me to a good reference
with application to collaborative filtering/topic modeling ? Stochastic matrix decomposition
is what we can do in this PR now https://github.com/apache/spark/pull/3221....
For MAP loss, I will open up a PR in a week through JIRA https://issues.apache.org/jira/browse/SPARK6323...I
am very curious how much slower we get compared to stochastic matrix decomposition using ALS
> Quadratic Minimization for MLlib ALS
> 
>
> Key: SPARK2426
> URL: https://issues.apache.org/jira/browse/SPARK2426
> Project: Spark
> Issue Type: New Feature
> Components: MLlib
> Affects Versions: 1.3.0
> Reporter: Debasish Das
> Assignee: Debasish Das
> Original Estimate: 504h
> Remaining Estimate: 504h
>
> Current ALS supports least squares and nonnegative least squares.
> I presented ADMM and IPM based Quadratic Minimization solvers to be used for the following
ALS problems:
> 1. ALS with bounds
> 2. ALS with L1 regularization
> 3. ALS with Equality constraint and bounds
> Initial runtime comparisons are presented at Spark Summit.
> http://sparksummit.org/2014/talk/quadraticprogramingsolverfornonnegativematrixfactorizationwithspark
> Based on Xiangrui's feedback I am currently comparing the ADMM based Quadratic Minimization
solvers with IPM based QpSolvers and the default ALS/NNLS. I will keep updating the runtime
comparison results.
> For integration the detailed plan is as follows:
> 1. Add QuadraticMinimizer and Proximal algorithms in mllib.optimization
> 2. Integrate QuadraticMinimizer in mllib ALS

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

To unsubscribe, email: issuesunsubscribe@spark.apache.org
For additional commands, email: issueshelp@spark.apache.org
