[GitHub] madlib issue #243: MLP: Add minibatch gradient descent solver

[asfgit]

Github user asfgit commented on the issue:

https://github.com/apache/madlib/pull/243
  

Refer to this link for build results (access rights to CI server needed): 
https://builds.apache.org/job/madlib-pr-build/380/



---

[GitHub] madlib issue #244: Changes for Personalized Page Rank : Jira:1084

[asfgit]

Github user asfgit commented on the issue:

https://github.com/apache/madlib/pull/244
  

Refer to this link for build results (access rights to CI server needed): 
https://builds.apache.org/job/madlib-pr-build/379/



---

[GitHub] madlib issue #243: MLP: Add minibatch gradient descent solver

[asfgit]

Github user asfgit commented on the issue:

https://github.com/apache/madlib/pull/243
  

Refer to this link for build results (access rights to CI server needed): 
https://builds.apache.org/job/madlib-pr-build/378/



---

[GitHub] madlib pull request #244: Changes for Personalized Page Rank : Jira:1084

[hpandeycodeit]

GitHub user hpandeycodeit opened a pull request:

https://github.com/apache/madlib/pull/244

Changes for Personalized Page Rank : Jira:1084

Jira : 1084
This PR contains changes for Personalized Page Rank.

-  Added extra parameter, nodes_of_interest in main pagerank function. 
-  Added a new Function get_query_params_for_ppr  in pagerank.py_in to 
calculate random_jump_probabilty based on the user provided input nodes. 
-  Added a condition, when the user provided nodes are present then 
Personalized Page Rank will be executed otherwise regular Page Rank will run. 
-  Added an example function in pagerank.sql_in
- The extra parameter nodes_of_interest is also added in the calling 
functions in pagerank.sql_in

You can merge this pull request into a Git repository by running:

$ git pull https://github.com/hpandeycodeit/incubator-madlib graph_1084

Alternatively you can review and apply these changes as the patch at:

https://github.com/apache/madlib/pull/244.patch

To close this pull request, make a commit to your master/trunk branch
with (at least) the following in the commit message:

This closes #244


commit ed1e364db205f104379270529d3eff694a589651
Author: hpandeycodeit 
Date:   2018-03-16T22:15:51Z

Changes for Personalized Page Rank : Jira:1084




---

[GitHub] madlib pull request #240: MLP: Fix step size initialization based on learnin...

[kaknikhil]

Github user kaknikhil commented on a diff in the pull request:

https://github.com/apache/madlib/pull/240#discussion_r175224785
  
--- Diff: src/ports/postgres/modules/convex/mlp_igd.py_in ---
@@ -112,6 +112,7 @@ def mlp(schema_madlib, source_table, output_table, 
independent_varname,
 num_output_nodes = 0
 classes = []
 dependent_type = get_expr_type(dependent_varname, source_table)
+classes_str = None
--- End diff --

we don't really need this `classes_str` variable, right ?


---

[GitHub] madlib issue #243: MLP: Add minibatch gradient descent solver

[asfgit]

Github user asfgit commented on the issue:

https://github.com/apache/madlib/pull/243
  

Refer to this link for build results (access rights to CI server needed): 
https://builds.apache.org/job/madlib-pr-build/377/



---

[GitHub] madlib pull request #243: MLP: Add minibatch gradient descent solver

[njayaram2]

GitHub user njayaram2 opened a pull request:

https://github.com/apache/madlib/pull/243

MLP: Add minibatch gradient descent solver

JIRA: MADLIB-1206

This commit adds support for mini-batch based gradient descent for MLP.
If the input table contains a 2D matrix for independent variable,
minibatch is automatically used as the solver. Two minibatch specific
optimizers are also introduced: batch_size and n_epochs.
- batch_size is defaulted to min(200, buffer_size), where buffer_size is
  equal to the number of original input rows packed into a single row in
  the matrix.
- n_epochs is the number of times all the batches in a buffer are
  iterated over (default 1).

Other changes include:
- dependent variable in the minibatch solver is also a matrix now. It
  was initially a vector.
- Randomize the order of processing a batch within an epoch.
- MLP minibatch currently doesn't support weights param, an error is
  thrown now.
- Delete an unused type named mlp_step_result.
- Add unit tests for newly added functions in python file.

Co-authored-by: Rahul Iyer 
Co-authored-by: Nikhil Kak 

Closes #243

You can merge this pull request into a Git repository by running:

$ git pull https://github.com/madlib/madlib 
mlp-minibatch-with-preprocessed-data-rebased

Alternatively you can review and apply these changes as the patch at:

https://github.com/apache/madlib/pull/243.patch

To close this pull request, make a commit to your master/trunk branch
with (at least) the following in the commit message:

This closes #243


commit d9306f7c6a44f64c53df13c34759da55468c4d26
Author: Nandish Jayaram 
Date:   2018-02-28T00:51:42Z

MLP: Add minibatch gradient descent solver

JIRA: MADLIB-1206

This commit adds support for mini-batch based gradient descent for MLP.
If the input table contains a 2D matrix for independent variable,
minibatch is automatically used as the solver. Two minibatch specific
optimizers are also introduced: batch_size and n_epochs.
- batch_size is defaulted to min(200, buffer_size), where buffer_size is
  equal to the number of original input rows packed into a single row in
  the matrix.
- n_epochs is the number of times all the batches in a buffer are
  iterated over (default 1).

Other changes include:
- dependent variable in the minibatch solver is also a matrix now. It
  was initially a vector.
- Randomize the order of processing a batch within an epoch.
- MLP minibatch currently doesn't support weights param, an error is
  thrown now.
- Delete an unused type named mlp_step_result.
- Add unit tests for newly added functions in python file.

Co-authored-by: Rahul Iyer 
Co-authored-by: Nikhil Kak 

Closes #243




---