[jira] [Commented] (SPARK-4638) Spark's MLlib SVM classification to include Kernels like Gaussian / (RBF) to find non linear boundaries
[ https://issues.apache.org/jira/browse/SPARK-4638?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15840711#comment-15840711 ] Joseph K. Bradley commented on SPARK-4638: -- Commenting here b/c of the recent dev list thread: Non-linear kernels for SVMs in Spark would be great to have. The main barriers are: * Kernelized SVM training is hard to distribute. Naive methods require a lot of communication. To get this feature into Spark, we'd need to do proper background research and write up a good design. * Other ML algorithms are arguably more in demand and still need improvements (as of the date of this comment). Tree ensembles are first-and-foremost in my mind. > Spark's MLlib SVM classification to include Kernels like Gaussian / (RBF) to > find non linear boundaries > --- > > Key: SPARK-4638 > URL: https://issues.apache.org/jira/browse/SPARK-4638 > Project: Spark > Issue Type: New Feature > Components: MLlib >Reporter: madankumar s > Labels: Gaussian, Kernels, SVM > Attachments: kernels-1.3.patch > > > SPARK MLlib Classification Module: > Add Kernel functionalities to SVM Classifier to find non linear patterns -- 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] [Commented] (SPARK-4638) Spark's MLlib SVM classification to include Kernels like Gaussian / (RBF) to find non linear boundaries
[ https://issues.apache.org/jira/browse/SPARK-4638?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14493180#comment-14493180 ] Sean Owen commented on SPARK-4638: -- [~mandar2812] Spark does not use patches in JIRA but uses pull requests. Also changes should be vs master, not a branch. https://cwiki.apache.org/confluence/display/SPARK/Contributing+to+Spark Spark's MLlib SVM classification to include Kernels like Gaussian / (RBF) to find non linear boundaries --- Key: SPARK-4638 URL: https://issues.apache.org/jira/browse/SPARK-4638 Project: Spark Issue Type: New Feature Components: MLlib Reporter: madankumar s Labels: Gaussian, Kernels, SVM Attachments: kernels-1.3.patch SPARK MLlib Classification Module: Add Kernel functionalities to SVM Classifier to find non linear patterns -- 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] [Commented] (SPARK-4638) Spark's MLlib SVM classification to include Kernels like Gaussian / (RBF) to find non linear boundaries
[ https://issues.apache.org/jira/browse/SPARK-4638?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14493347#comment-14493347 ] Apache Spark commented on SPARK-4638: - User 'mandar2812' has created a pull request for this issue: https://github.com/apache/spark/pull/5503 Spark's MLlib SVM classification to include Kernels like Gaussian / (RBF) to find non linear boundaries --- Key: SPARK-4638 URL: https://issues.apache.org/jira/browse/SPARK-4638 Project: Spark Issue Type: New Feature Components: MLlib Reporter: madankumar s Labels: Gaussian, Kernels, SVM Attachments: kernels-1.3.patch SPARK MLlib Classification Module: Add Kernel functionalities to SVM Classifier to find non linear patterns -- 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] [Commented] (SPARK-4638) Spark's MLlib SVM classification to include Kernels like Gaussian / (RBF) to find non linear boundaries
[ https://issues.apache.org/jira/browse/SPARK-4638?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14300012#comment-14300012 ] Mandar Chandorkar commented on SPARK-4638: -- Hello all, I have been working on an implementation of Kernels/Kernel Matrices as a part of my Masters thesis at KU Leuven. I have implemented RBF Polynomial Kernels for SVMs. I have drawn up a hierarchy of classes/interfaces which can be extended to implement other Kernels as well. I have made a new module within the mllib code. This is my first attempt at contributing to spark (and open source) so my code might be messy. To summarize I have worked on the following. 1) Class hierarchy for SVM Kernels, with unit tests. 2) Entropy based subset selection for low rank approximation of Large Kernel Matrices. 3) Kernels for density estimation, with 'plug in' based optimum bandwidth selection. I have the code on a local branch, I can push it to my fork and do a pull request, but before that is there anything else I should do (apart from checking the code style and all that)? I can also make a short design document describing the class hierarchies and how they are connected. Thank you Spark's MLlib SVM classification to include Kernels like Gaussian / (RBF) to find non linear boundaries --- Key: SPARK-4638 URL: https://issues.apache.org/jira/browse/SPARK-4638 Project: Spark Issue Type: New Feature Components: MLlib Reporter: madankumar s Labels: Gaussian, Kernels, SVM SPARK MLlib Classification Module: Add Kernel functionalities to SVM Classifier to find non linear patterns -- 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
