IRC logs of #shogun for Wednesday, 2014-06-11

--- Log opened Wed Jun 11 00:00:27 2014
-!- lambday [67157f4f@gateway/web/freenode/ip.103.21.127.79] has joined #shogun00:04
-!- shogun-notifier- [~irker@7nn.de] has joined #shogun00:29
shogun-notifier-shogun: lambday :develop * d194676 / / (12 files): https://github.com/shogun-toolbox/shogun/commit/d194676f9fee8e3597a59ea790d1b9dc27a74d5e00:29
shogun-notifier-shogun: added proper lapack check to address issue #229100:29
shogun-notifier-shogun: Soumyajit De :develop * 0e4bf9f / / (12 files): https://github.com/shogun-toolbox/shogun/commit/0e4bf9fe5a97e6318cf8f242e0c1553d51dcca1f00:29
shogun-notifier-shogun: Merge pull request #2292 from lambday/develop00:29
shogun-notifier-shogun:00:29
shogun-notifier-shogun: added proper lapack check to address issue #229100:29
shogun-buildbotbuild #2339 of bsd1 - libshogun is complete: Failure [failed compile test]  Build details are at http://buildbot.shogun-toolbox.org/builders/bsd1%20-%20libshogun/builds/2339  blamelist: lambday <heavensdevil6909@gmail.com>00:34
-!- thoralf [~thoralf@91-65-141-142-dynip.superkabel.de] has joined #shogun00:34
thoralfHeyhey.00:35
shogun-buildbotbuild #2340 of bsd1 - libshogun is complete: Failure [failed compile test]  Build details are at http://buildbot.shogun-toolbox.org/builders/bsd1%20-%20libshogun/builds/2340  blamelist: Soumyajit De <heavensdevil6909@gmail.com>00:38
shogun-notifier-shogun: Wu Lin :develop * 358fe87 / examples/undocumented/libshogun/variational_approx_example.cpp: https://github.com/shogun-toolbox/shogun/commit/358fe87eabdaefcaf0d8a82d53b4abd5481e4e5600:38
shogun-notifier-shogun: using small dataset00:38
shogun-notifier-shogun: tklein23 :develop * 3a6592e / examples/undocumented/libshogun/variational_approx_example.cpp: https://github.com/shogun-toolbox/shogun/commit/3a6592e27fdb976e75a68bbbc7069b9f181a3ddf00:38
shogun-notifier-shogun: Merge pull request #2286 from yorkerlin/variational-example00:38
shogun-notifier-shogun:00:38
shogun-notifier-shogun: variational_approx_example using small dataset (for memory check)00:38
shogun-notifier-shogun: Wu Lin :develop * a64cbf0 / tests/unit/machine/gp/ProbitLikelihood_unittest.cc: https://github.com/shogun-toolbox/shogun/commit/a64cbf07aa7fe5143089dbda3f4f2c6248ad20cc00:44
shogun-notifier-shogun: fix the memory leak issue00:44
shogun-notifier-shogun: Wu Lin :develop * 851a0be / src/shogun/machine/gp/ (2 files): https://github.com/shogun-toolbox/shogun/commit/851a0bea670fa93d7a8e174fd309ec947080545400:44
shogun-notifier-shogun: add the base class for KL methods00:44
shogun-notifier-shogun: tklein23 :develop * cac56dd / src/shogun/machine/gp/ (2 files): https://github.com/shogun-toolbox/shogun/commit/cac56dd961d573f6fde0dfded85b05e3fb848add00:44
shogun-notifier-shogun: Merge pull request #2287 from yorkerlin/develop00:44
shogun-notifier-shogun:00:44
shogun-notifier-shogun: The base KL method class00:44
-!- PirosB3 [~pirosb3@host80-223-dynamic.246-95-r.retail.telecomitalia.it] has quit [Ping timeout: 265 seconds]00:56
-!- PirosB3 [~pirosb3@host80-223-dynamic.246-95-r.retail.telecomitalia.it] has joined #shogun01:05
-!- thoralf [~thoralf@91-65-141-142-dynip.superkabel.de] has quit [Ping timeout: 252 seconds]01:07
-!- thoralf [~thoralf@91-65-141-142-dynip.superkabel.de] has joined #shogun01:24
-!- thoralf [~thoralf@91-65-141-142-dynip.superkabel.de] has quit [Quit: Konversation terminated!]01:31
shogun-buildbotbuild #2341 of bsd1 - libshogun is complete: Failure [failed compile test]  Build details are at http://buildbot.shogun-toolbox.org/builders/bsd1%20-%20libshogun/builds/2341  blamelist: Wu Lin <yorker.lin@gmail.com>, tklein23 <tklein23@users.noreply.github.com>01:46
-!- pickle27 [~pickle27@192-0-136-118.cpe.teksavvy.com] has joined #shogun01:49
-!- khalednasr [~k.nasr92@41.69.158.33] has quit [Ping timeout: 240 seconds]02:26
-!- pickle27 [~pickle27@192-0-136-118.cpe.teksavvy.com] has quit [Remote host closed the connection]02:27
shogun-buildbotbuild #24 of nightly_fedora is complete: Failure [failed git]  Build details are at http://buildbot.shogun-toolbox.org/builders/nightly_fedora/builds/24  blamelist: lambday <heavensdevil6909@gmail.com>, Parijat Mazumdar <mazumdarparijat@gmail.com>, Wu Lin <yorker.lin@gmail.com>, tklein23 <tklein23@users.noreply.github.com>, Soumyajit De <heavensdevil6909@gmail.com>,03:00
shogun-buildbotFernando Iglesias <fernando.iglesiasg@gmail.com>03:00
-!- PirosB3 [~pirosb3@host80-223-dynamic.246-95-r.retail.telecomitalia.it] has quit [Quit: PirosB3]03:18
shogun-buildbotbuild #338 of debian wheezy - memcheck is complete: Failure [failed memory check]  Build details are at http://buildbot.shogun-toolbox.org/builders/debian%20wheezy%20-%20memcheck/builds/338  blamelist: lambday <heavensdevil6909@gmail.com>, Soumyajit De <heavensdevil6909@gmail.com>03:38
shogun-notifier-shogun: lambday :develop * f3e1f59 / src/shogun/statistics/ (2 files): https://github.com/shogun-toolbox/shogun/commit/f3e1f598412d46a9978b9ff312c70387737adf8503:41
shogun-notifier-shogun: prevent failure in class_list.cpp when LAPACK is not present03:41
shogun-notifier-shogun: Soumyajit De :develop * df92341 / src/shogun/statistics/ (2 files): https://github.com/shogun-toolbox/shogun/commit/df92341eff532339849dd5c7b405f1e90fee815a03:41
shogun-notifier-shogun: Merge pull request #2294 from lambday/develop03:41
shogun-notifier-shogun:03:41
shogun-notifier-shogun: prevent failure in class_list.cpp when LAPACK is not present03:41
-!- travis-ci [~travis-ci@ec2-54-237-208-250.compute-1.amazonaws.com] has joined #shogun03:56
travis-ci[travis-ci] it's Soumyajit De's turn to pay the next round of drinks for the massacre he caused in shogun-toolbox/shogun: http://travis-ci.org/shogun-toolbox/shogun/builds/2727240003:56
-!- travis-ci [~travis-ci@ec2-54-237-208-250.compute-1.amazonaws.com] has left #shogun []03:56
-!- soumyaC [uid15286@gateway/web/irccloud.com/x-zmdztwwnxsgnkaql] has quit [Quit: Connection closed for inactivity]04:26
-!- lambday [67157f4f@gateway/web/freenode/ip.103.21.127.79] has quit [Ping timeout: 246 seconds]05:40
-!- shogun-notifier- [~irker@7nn.de] has quit [Quit: transmission timeout]06:42
-!- abinash_panda [~abinash@117.200.236.154] has joined #shogun07:58
shogun-buildbotbuild #823 of nightly_default is complete: Failure [failed notebooks]  Build details are at http://buildbot.shogun-toolbox.org/builders/nightly_default/builds/823  blamelist: lambday <heavensdevil6909@gmail.com>, Parijat Mazumdar <mazumdarparijat@gmail.com>, Wu Lin <yorker.lin@gmail.com>, tklein23 <tklein23@users.noreply.github.com>, Soumyajit De08:12
shogun-buildbot<heavensdevil6909@gmail.com>, Fernando Iglesias <fernando.iglesiasg@gmail.com>08:12
-!- lisitsyn [~qdrgsm@80.252.20.67] has joined #shogun08:18
shogun-buildbotbuild #2342 of bsd1 - libshogun is complete: Failure [failed test]  Build details are at http://buildbot.shogun-toolbox.org/builders/bsd1%20-%20libshogun/builds/2342  blamelist: lambday <heavensdevil6909@gmail.com>, Soumyajit De <heavensdevil6909@gmail.com>08:21
-!- abinash_panda [~abinash@117.200.236.154] has quit [Ping timeout: 245 seconds]09:14
-!- lisitsyn [~qdrgsm@80.252.20.67] has quit [Quit: Leaving.]09:36
-!- khalednasr [~k.nasr92@41.69.223.215] has joined #shogun09:54
shogun-buildbotbuild #339 of debian wheezy - memcheck is complete: Success [build successful]  Build details are at http://buildbot.shogun-toolbox.org/builders/debian%20wheezy%20-%20memcheck/builds/33910:11
-!- khalednasr [~k.nasr92@41.69.223.215] has quit [Ping timeout: 260 seconds]10:13
-!- PirosB3 [~pirosb3@host80-223-dynamic.246-95-r.retail.telecomitalia.it] has joined #shogun10:39
-!- PirosB3 [~pirosb3@host80-223-dynamic.246-95-r.retail.telecomitalia.it] has quit [Quit: PirosB3]11:12
-!- Saurabh7 [~Saurabh7@117.200.188.89] has joined #shogun11:15
-!- tp199911 [863a27df@gateway/web/freenode/ip.134.58.39.223] has joined #shogun11:28
-!- PirosB3 [~pirosb3@host80-223-dynamic.246-95-r.retail.telecomitalia.it] has joined #shogun11:50
-!- lisitsyn [~lisitsin@mxs.kg.ru] has joined #shogun12:03
-!- khalednasr [~k.nasr92@41.69.235.207] has joined #shogun12:43
-!- Saurabh7 [~Saurabh7@117.200.188.89] has quit [Quit: Leaving]13:03
-!- shogun-notifier- [~irker@7nn.de] has joined #shogun13:13
shogun-notifier-shogun: Parijat Mazumdar :develop * 79ac6c8 / / (4 files): https://github.com/shogun-toolbox/shogun/commit/79ac6c865d9d587720cd3e315d2522572d5444c213:13
shogun-notifier-shogun: modular API, bug fix for C4.513:13
shogun-notifier-shogun: Fernando Iglesias :develop * 4f85314 / / (4 files): https://github.com/shogun-toolbox/shogun/commit/4f85314a51267c411318279e3d1dd46373abdad213:13
shogun-notifier-shogun: Merge pull request #2293 from mazumdarparijat/rf13:13
shogun-notifier-shogun:13:13
shogun-notifier-shogun: modular API, bug fix for C4.513:13
shogun-buildbotbuild #2343 of bsd1 - libshogun is complete: Failure [failed test]  Build details are at http://buildbot.shogun-toolbox.org/builders/bsd1%20-%20libshogun/builds/2343  blamelist: Parijat Mazumdar <mazumdarparijat@gmail.com>13:20
shogun-buildbotbuild #2344 of bsd1 - libshogun is complete: Failure [failed test]  Build details are at http://buildbot.shogun-toolbox.org/builders/bsd1%20-%20libshogun/builds/2344  blamelist: Fernando Iglesias <fernando.iglesiasg@gmail.com>13:25
-!- khalednasr [~k.nasr92@41.69.235.207] has quit [Quit: Leaving]13:27
-!- travis-ci [~travis-ci@ec2-54-82-55-141.compute-1.amazonaws.com] has joined #shogun14:17
travis-ci[travis-ci] it's Fernando Iglesias's turn to pay the next round of drinks for the massacre he caused in shogun-toolbox/shogun: http://travis-ci.org/shogun-toolbox/shogun/builds/2729954214:17
-!- travis-ci [~travis-ci@ec2-54-82-55-141.compute-1.amazonaws.com] has left #shogun []14:17
-!- Saurabh7 [~Saurabh7@117.200.188.89] has joined #shogun14:20
-!- kislay [~Abhijeet@103.240.206.231] has joined #shogun14:21
-!- PirosB3 [~pirosb3@host80-223-dynamic.246-95-r.retail.telecomitalia.it] has quit [Quit: PirosB3]15:17
-!- shogun-notifier- [~irker@7nn.de] has quit [Quit: transmission timeout]16:13
-!- pickle27 [~pickle27@192-0-136-118.cpe.teksavvy.com] has joined #shogun16:14
-!- lisitsyn [~lisitsin@mxs.kg.ru] has quit [Quit: Leaving.]16:19
-!- pickle27 [~pickle27@192-0-136-118.cpe.teksavvy.com] has quit [Remote host closed the connection]16:20
-!- tp199911 [863a27df@gateway/web/freenode/ip.134.58.39.223] has quit [Quit: Page closed]16:41
-!- abinash_panda [~abinash@117.200.235.72] has joined #shogun19:14
-!- Saurabh7 [~Saurabh7@117.200.188.89] has quit [Quit: Leaving]19:36
-!- thoralf [~thoralf@91-65-141-142-dynip.superkabel.de] has joined #shogun20:06
thoralfHeyhey20:06
thoralfabinash_panda: Good morning ,)20:07
abinash_pandahey thoralf20:26
abinash_pandaits actually night over here ;)20:26
thoralfabinash_panda: What are you currently working on?20:39
abinash_pandaCurrently, I am working on the feature hashing. The gist you had sent me today was really helpful :)20:39
abinash_pandathoralf: I have a few questions..20:40
thoralfabinash_panda: Shoot.20:40
abinash_pandathoralf: First, what should be class name of hashed features, I propose HashedSparseMultilabelFeatures. Any suggestions?20:40
thoralfI think "Sparse" is not neccessary.20:41
thoralfnecessary20:41
abinash_pandathoralf: Okay, so we can go with HashedMultilabelFeatures20:41
abinash_pandathoralf: But, I would be supporting mainly hashed features, so I was thinking of adding *Sparse*. Okay, no problem20:42
thoralfIf you find this important, let's call it HashedSparse...20:42
abinash_pandaOkay, fine.20:43
abinash_pandathoralf: Second, the user should provide the seeds for hashing right?20:43
thoralfabinash_panda: Well, for the beginning, you can just say seed for the i-th label is "i" ;)20:44
abinash_pandaSo, I am thinking the constructor would be something like CHashedSparseMultilabelFeatures<ST>(CSparseFeatures* feats, int32_t d, SGVector<uint32_t> seeds,...)20:44
thoralfWhat's d?20:44
abinash_pandad is the dimension of the new feature20:45
thoralfAh, of course.20:45
thoralfYes.20:45
abinash_pandaSo, if the user doesn't provide the seeds we can go for seed of i-th label as "i"20:45
thoralfYes, that would be helpful.20:46
abinash_pandaso another constructor would be something like CHashedSparseMultilabelFeatures(feats, dim, num_classes, ...)20:46
thoralfnum_labels?20:46
thoralfLet me check. ;)20:47
abinash_pandaokay20:47
thoralfnum_classes, you're right.20:48
thoralfThis is a bit confusing.20:48
abinash_pandaokay...num_classes means the total number of classes we are having...right?20:49
thoralfabinash_panda: Yes.20:49
thoralfAnd num_labels should be called num_examples to avoid confusion.20:50
thoralfBut it's too late now.20:50
thoralf(It's never too late... but. ;)20:50
abinash_pandayeah...I would try to modify it wherever I can20:50
thoralfabinash_panda: I guess the implementation is straight forward.  Do you think you have to implement more that get_joint_feature_vector and get_dim?20:51
abinash_pandaget_joint_feature and get_dim are the methods of a StructuredModel, but I am implementing a DotFeature class.20:52
abinash_pandaI am thinking of having a class for hashed features and not modifying the MultilabelModel20:53
abinash_pandaAny suggestions?20:53
thoralfI think it would be easier to don't implement own features, because the joint features is not a tensor any more.20:56
abinash_pandaNow, I am getting confused.20:57
abinash_pandaIf you could explain me the hashing once again.20:58
abinash_pandaWhat I thought that we would be hashing the feature vector, so it would be better to implement our own features.20:59
thoralfnormal so learning optimizes < w ; PSI(x,y) > with PSI(x,y) = x (x) y where (x) denotes tensor product21:04
thoralfhashing optimizes < w ; PSI(x,y) > with PSI(x,y) = sum_{i \in y} phi(x,i)21:06
thoralfwhere phi is a hashing function parametrized by i21:06
thoralfor sum_i [[y_i == 1]] * phi_i(x)21:07
thoralfSame thing, different notation21:07
abinash_pandaOkay, now I get it.21:08
abinash_pandaPreviously, I was thinking of something else.21:08
abinash_pandaso, now just PSI(x, y) changes meaning I have to change get_joint_feature_vector and get_dim21:08
abinash_pandaSo, now the MultilabelModel should have a constructor something like this MultilabelModel(CFeatures* features, CStructuredLabels* labels, bool hashing = false, int32_t dim = 0)21:10
thoralfI still would create a new Hashing(Sparse;))MultilabelModel21:18
thoralfThere is some duplication, but the functionality would be too different.21:18
abinash_pandaYeah that would be better.21:18
thoralfIf we see too much duplicated behaviour, we can talk about it.21:19
thoralfAh, well.  You also have to implement a slightly different version of argmax.21:19
thoralfBecause the current one assumes that each class has it's own features.21:19
thoralfThe new one can just do < w, phi_(x) > to find out the score for label i21:20
abinash_pandayou mean <w, phi_i(x)> where phi_i(x) would be hashing function parameterized by i..right?21:22
thoralfYeah.21:22
abinash_pandaOkay. Got it.21:23
thoralfThis can be used to get the score of label i.21:23
thoralfIt still decomposes in a linear way, so we can put the sum into the scalar product or outside.21:23
thoralf< w ; sum_{i \in y} phi(x,i) > = sum_{i \in y} < w ; phi(x,i) >21:24
abinash_pandaand if the score of label i > 0, then we should predict i21:25
thoralfExact.21:25
thoralfAs usual :)21:25
abinash_pandaOkay. So, I going to implement it now :)21:26
thoralfYeah, good luck.21:27
thoralfYou should start thinking about some small plot/example/ipython notebook.21:27
thoralfOnly gathering ideas what to evaluate/write/plot on which (toy?) data...21:28
abinash_pandaYeah...I would do it. I was writing it earlier, and suddenly my computer got crashed :(21:29
abinash_pandaAll of it got deleted, as I had to format it.21:30
abinash_pandaSo, I would do it.21:30
abinash_pandaBTW, have you used the PrimalMosekSOSVM solver?21:31
-!- lisitsyn [~qdrgsm@85.114.187.192] has joined #shogun21:46
kislayhey lisitsyn :)21:46
lisitsynkislay: hey21:46
kislaycongo for the MSC man :D21:46
lisitsynkislay: thanks!21:47
lisitsynkislay: how is it going?21:47
kislayFine. I have tried to implement the macro thing you commented there.21:47
lisitsynkislay: cool, is it better now?21:48
kislayyeah21:49
kislaywas able to cut lots of code.21:49
kislaySee the PR when you get free. I have to keep improving it.21:50
thoralfabinash_panda: No, didn't use it so far.21:50
thoralfHey Master L21:51
kislayHey T!! how's you? :)21:51
thoralfkislay: I'm fine. :)21:52
abinash_pandathoralf: Actually, I have used it on my machine and found that it took a lot of time to train.21:52
thoralfVery hot here and glad it's evening and got a bit colder :)21:52
thoralfabinash_panda: Yeah, they all take some time.  I thing SGD was the fastest one.21:52
thoralfthink21:53
kislayhah! we have 46 degrees here! in India!!21:53
abinash_pandathoralf: The toy example provided in so_multiclass.cpp worked fine, but when I had increased the features and examples in hundreds of thousands, I had to reboot my computer.21:53
thoralfkislay: degree celsius?21:53
kislayyup yup21:53
thoralfabinash_panda: Before starting the script, call "ulimit -v <kbytes>" to save your machine ;)21:54
kislaythoralf, Thats actually normal summer temp. here.21:54
thoralfSet it to something like 80% of your RAM.21:54
thoralfkislay: That's crazy.  Who's responsible for this decision? ;)21:54
abinash_pandathoralf: Okay. I didn't know about. Thanks :)21:55
thoralfabinash_panda: Must be called in the same shell as used for running the command.21:55
thoralfHas no affect on already running processes or other shells.21:55
abinash_pandathoralf: yeah..it would use it21:56
kislaythoralf, the equator crosses India... probably thats why!21:57
lisitsynthoralf: hey21:59
-!- kislay [~Abhijeet@103.240.206.231] has quit [Ping timeout: 245 seconds]22:12
-!- abinash_panda [~abinash@117.200.235.72] has quit [Quit: leaving]22:13
-!- zxtx [~zv@ool-45763ca9.dyn.optonline.net] has quit [Ping timeout: 260 seconds]22:22
-!- lisitsyn [~qdrgsm@85.114.187.192] has quit [Read error: Connection reset by peer]22:32
-!- lisitsyn [~qdrgsm@85.114.187.192] has joined #shogun22:32
-!- Netsplit *.net <-> *.split quits: sonney2k, naywhayare22:40
-!- Netsplit over, joins: sonney2k, naywhayare22:40
-!- lisitsyn [~qdrgsm@85.114.187.192] has quit [Read error: Connection reset by peer]23:45
-!- khalednasr [~k.nasr92@41.69.234.202] has joined #shogun23:59
--- Log closed Thu Jun 12 00:00:29 2014

Generated by irclog2html.py 2.10.0 by Marius Gedminas - find it at mg.pov.lt!