[GitHub] spark pull request: [Minor][Mllib] Simplify loss function

2015-01-06 Thread SparkQA
Github user SparkQA commented on the pull request: https://github.com/apache/spark/pull/3899#issuecomment-68837409 [Test build #25093 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/25093/consoleFull) for PR 3899 at commit [`a3f83ca`](https://githu

[GitHub] spark pull request: [Minor][Mllib] Simplify loss function

2015-01-06 Thread viirya
Github user viirya commented on the pull request: https://github.com/apache/spark/pull/3899#issuecomment-68837277 Hi @mengxr, Thanks for comment. I may be wrong, but I think that we should branch based on `sign(label)` instead of `sign(label * margin)`? Because according to th

[GitHub] spark pull request: [Minor][Mllib] Simplify loss function

2015-01-05 Thread viirya
Github user viirya commented on the pull request: https://github.com/apache/spark/pull/3899#issuecomment-68800241 @mengxr Thanks for that. I will do it later. --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your projec

[GitHub] spark pull request: [Minor][Mllib] Simplify loss function

2015-01-05 Thread mengxr
Github user mengxr commented on the pull request: https://github.com/apache/spark/pull/3899#issuecomment-68749063 @viirya Thanks for the improvement! We could make this computation more accurate. We should branch based on `sign(label) * margin`, similar to https://github.com/

[GitHub] spark pull request: [Minor][Mllib] Simplify loss function

2015-01-05 Thread AmplabJenkins
Github user AmplabJenkins commented on the pull request: https://github.com/apache/spark/pull/3899#issuecomment-68693770 Test PASSed. Refer to this link for build results (access rights to CI server needed): https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/25

[GitHub] spark pull request: [Minor][Mllib] Simplify loss function

2015-01-05 Thread SparkQA
Github user SparkQA commented on the pull request: https://github.com/apache/spark/pull/3899#issuecomment-68693757 [Test build #25053 has finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/25053/consoleFull) for PR 3899 at commit [`2bc5712`](https://gith

[GitHub] spark pull request: [Minor][Mllib] Simplify loss function

2015-01-05 Thread srowen
Github user srowen commented on the pull request: https://github.com/apache/spark/pull/3899#issuecomment-68687443 +1 looks like a small good improvement. --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project doe

[GitHub] spark pull request: [Minor][Mllib] Simplify loss function

2015-01-05 Thread SparkQA
Github user SparkQA commented on the pull request: https://github.com/apache/spark/pull/3899#issuecomment-68686539 [Test build #25053 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/25053/consoleFull) for PR 3899 at commit [`2bc5712`](https://githu

[GitHub] spark pull request: [Minor][Mllib] Simplify loss function

2015-01-05 Thread viirya
GitHub user viirya opened a pull request: https://github.com/apache/spark/pull/3899 [Minor][Mllib] Simplify loss function This is a minor pr where I think that we can simply take minus of `margin` here, instead of subtracting `margin`. Mathematically, they are equal. But t