IRC logs of #shogun for Thursday, 2013-05-09

« Wednesday, 2013-05-08 Index Friday, 2013-05-10 »
--- Log opened Thu May 09 00:00:37 2013
-!- iglesiasg [d58f32bd@gateway/web/freenode/ip.213.143.50.189] has quit [Quit: Page closed]00:11
@sonney2kvan51, yeah remove that legacy crap00:13
van51sonney2k: ok, got it ;)00:16
van51on another note, is there a reason why operator[] isn't overloaded in CDynamicObjectArray?00:16
van51not that it's important, it just seems strange :p00:17
@sonney2kvan51, well it is usually new'd so you would have to (*array)[1] etc00:19
@sonney2kbut feel free :D00:19
-!- goldbug [~quassel@global-2-11.nat.csx.cam.ac.uk] has joined #shogun00:21
van51hehe just for consistency :D00:21
van51sonney2k: actually, maybe all get_*_kernel() should go, and just have get_kernel(index_t idx)00:28
van51and maybe a get_last_kernel00:30
@wikingsonney2k: do we assure alignedness with SG_MALLOC?00:33
@wikingas i can see not :(00:46
-!- shogun-notifier- [~irker@7nn.de] has quit [Quit: transmission timeout]00:49
-!- goldbug [~quassel@global-2-11.nat.csx.cam.ac.uk] has quit [Remote host closed the connection]01:04
-!- foulwall [~foulwall@2001:da8:215:503:74db:1c21:5626:64bc] has joined #shogun01:20
-!- shogun-notifier- [~irker@7nn.de] has joined #shogun01:28
shogun-notifier-shogun: Viktor Gal :feature/PRNG * c5a21a8 / src/shogun/mathematics/Random.cpp,src/shogun/mathematics/Random.h: https://github.com/shogun-toolbox/shogun/commit/c5a21a80ea25b41d9d7fd2dde7d961c4da52f8fd01:28
shogun-notifier-shogun: Implement Ziggurat normal distrib sampler01:28
shogun-notifier-shogun: Viktor Gal :feature/PRNG * d52b026 / tests/unit/statistics/QuadraticTimeMMD_unittest.cc: https://github.com/shogun-toolbox/shogun/commit/d52b0263f7dc13c01c92e68f0731348c156c615401:28
shogun-notifier-shogun: Change to EXPECT_NEAR macro01:28
shogun-notifier-shogun: Viktor Gal :feature/PRNG * a44102d / src/shogun/mathematics/Random.cpp,src/shogun/mathematics/Random.h: https://github.com/shogun-toolbox/shogun/commit/a44102d8b355733d8c8830094cfabf703706003501:28
shogun-notifier-shogun: Random: allocate vectors on heap01:28
shogun-notifier-shogun: Viktor Gal :feature/PRNG * 68a7ab2 / tests/unit/mathematics/Random_unittest.cc: https://github.com/shogun-toolbox/shogun/commit/68a7ab28597cb674511f4c8acadbfb03a6b35e7101:28
shogun-notifier-shogun: Add unit test for normal_distrib01:28
-!- travis-ci [~travis-ci@ec2-107-22-117-126.compute-1.amazonaws.com] has joined #shogun01:33
travis-ci[travis-ci] it's Viktor Gal'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/700541401:33
-!- travis-ci [~travis-ci@ec2-107-22-117-126.compute-1.amazonaws.com] has left #shogun []01:33
shogun-notifier-shogun: Viktor Gal :feature/PRNG * c4cfc1a / src/shogun/mathematics/Random.h: https://github.com/shogun-toolbox/shogun/commit/c4cfc1ae534f396eb2c55f956789be85cc7cd00501:34
shogun-notifier-shogun: Random: include shogun/lib/common.h for stdint.h01:34
@wikingdoh01:38
@wikingwhy there's no UINT64_MAX on ubuntu? :)01:38
-!- travis-ci [~travis-ci@ec2-107-22-117-126.compute-1.amazonaws.com] has joined #shogun01:40
travis-ci[travis-ci] it's Viktor Gal'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/700555101:40
-!- travis-ci [~travis-ci@ec2-107-22-117-126.compute-1.amazonaws.com] has left #shogun []01:40
van51wiking: I am on ubuntu and I have it01:47
van51but for c++ I had to define __STDC_CONSTANT_MACROS first01:53
naywhayarewiking: uint64_t is a C99 type not a C++ type, maybe this is helpful: http://lists.freebsd.org/pipermail/freebsd-bugs/2012-December/051270.html :)02:05
naywhayare(can you tell I am procrastinating on my own work by randomly answering questions unnecessarily in IRC ??)02:06
shogun-buildbotbuild #334 of nightly_none is complete: Failure [failed compile]  Build details are at http://www.shogun-toolbox.org/buildbot/builders/nightly_none/builds/33403:15
sijinCould anyone tell me what will be the problem when travis could not compile?03:16
shogun-buildbotbuild #326 of nightly_all is complete: Failure [failed compile]  Build details are at http://www.shogun-toolbox.org/buildbot/builders/nightly_all/builds/32603:23
shogun-buildbotbuild #389 of nightly_default is complete: Failure [failed compile]  Build details are at http://www.shogun-toolbox.org/buildbot/builders/nightly_default/builds/38903:37
-!- shogun-notifier- [~irker@7nn.de] has quit [Quit: transmission timeout]04:34
sijinlisitsyn: It seems that tapkee checks the value of num_neighbors for every embedding method04:59
sijinlisitsyn: kpca doesn't use this , then some input would make the default value of num_neighbor (10) "invalid"05:03
-!- nube [~rho@116.90.239.3] has joined #shogun05:45
-!- nube [~rho@116.90.239.3] has quit [Ping timeout: 264 seconds]06:23
-!- sijin [~smuxi@144.214.222.109] has quit []06:32
-!- nube [~rho@116.90.239.3] has joined #shogun06:59
-!- foulwall [~foulwall@2001:da8:215:503:74db:1c21:5626:64bc] has quit [Remote host closed the connection]07:04
-!- nube [~rho@116.90.239.3] has quit [Read error: Connection reset by peer]07:32
-!- nube [~rho@116.90.239.3] has joined #shogun07:33
-!- deerishi [73f88294@gateway/web/freenode/ip.115.248.130.148] has joined #shogun07:34
-!- hushell [43bd6474@gateway/web/freenode/ip.67.189.100.116] has joined #shogun07:40
deerishi@sonny2k : could you take a look at this https://github.com/deerishi/shogun/compare/m107:41
deerishii did what you said,cloned another repo ,and pasted the files.07:42
deerishii did not touch the data,tests files07:42
deerishishould i send the pr?07:42
deerishi@HeikoS:could you also take a look at that?07:42
gsomixgood morning07:53
-!- sijin [~smuxi@144.214.222.109] has joined #shogun08:04
-!- hushell [43bd6474@gateway/web/freenode/ip.67.189.100.116] has quit [Ping timeout: 245 seconds]08:47
-!- mdragan [8d55007a@gateway/web/freenode/ip.141.85.0.122] has joined #shogun09:06
@sonney2knaywhayare, taht is the destiny of IRC users :)09:07
-!- iglesiasg [c1934d18@gateway/web/freenode/ip.193.147.77.24] has joined #shogun09:23
-!- mode/#shogun [+o iglesiasg] by ChanServ09:23
-!- iglesiasg [c1934d18@gateway/web/freenode/ip.193.147.77.24] has quit [Quit: Page closed]09:29
deerishi@HeikoS: I have sent the pr09:43
deerishiit does not contain any of the data/tests broken files09:43
deerishi@sonny2k : also the number of commits is 109:44
gsomixdeerishi, hi09:49
deerishihi gsomix09:49
gsomixdeerishi, please, sent your PR into develop branch, not master09:50
gsomix*send09:50
gsomixdeerishi, thanks!09:55
deerishi:)09:55
-!- deerishi [73f88294@gateway/web/freenode/ip.115.248.130.148] has quit [Ping timeout: 245 seconds]10:20
@wikingsonney2k: actually when we include stdint.h why dont we have a #define __STDC_LIMIT_MACROS10:29
@wikingso that we have access to the *_MAX macros?10:29
@wikingor just include <cstdint> instead....10:29
-!- shogun-notifier- [~irker@7nn.de] has joined #shogun10:33
shogun-notifier-shogun: Viktor Gal :feature/PRNG * c3e8f19 / src/shogun/lib/common.h: https://github.com/shogun-toolbox/shogun/commit/c3e8f19d8212eba84727c89df90052d48a9fc7e510:33
shogun-notifier-shogun: Define __STDC_LIMIT_MACROS before including stdint.h10:33
@wikingweelll that did not help :D10:35
-!- travis-ci [~travis-ci@ec2-107-22-117-126.compute-1.amazonaws.com] has joined #shogun10:39
travis-ci[travis-ci] it's Viktor Gal'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/701463410:39
-!- travis-ci [~travis-ci@ec2-107-22-117-126.compute-1.amazonaws.com] has left #shogun []10:39
@wikingmmm 3rd try :P10:46
shogun-notifier-shogun: Viktor Gal :feature/PRNG * ea4dceb / src/shogun/lib/common.h,src/shogun/mathematics/Random.h: https://github.com/shogun-toolbox/shogun/commit/ea4dceb5842790d9b3aba26ad024299137bdb8b710:46
shogun-notifier-shogun: Remove __STDC_LIMIT_MACROS macro and use std::numeric_limits10:46
-!- travis-ci [~travis-ci@ec2-23-22-231-136.compute-1.amazonaws.com] has joined #shogun10:51
travis-ci[travis-ci] it's Viktor Gal'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/701483510:51
-!- travis-ci [~travis-ci@ec2-23-22-231-136.compute-1.amazonaws.com] has left #shogun []10:51
shogun-notifier-shogun: Viktor Gal :feature/PRNG * e3143c5 / src/shogun/mathematics/Random.cpp: https://github.com/shogun-toolbox/shogun/commit/e3143c569f604f2ef7e26b02386e53ed3711ba0410:53
shogun-notifier-shogun: Use std::numeric_limit instead of macros10:53
-!- nube [~rho@116.90.239.3] has quit [Quit: Leaving.]11:02
-!- nube [~rho@116.90.239.3] has joined #shogun11:04
-!- lambday [3ba2174f@gateway/web/freenode/ip.59.162.23.79] has joined #shogun11:11
-!- travis-ci [~travis-ci@ec2-107-22-117-126.compute-1.amazonaws.com] has joined #shogun11:12
travis-ci[travis-ci] it's Viktor Gal'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/701493111:12
-!- travis-ci [~travis-ci@ec2-107-22-117-126.compute-1.amazonaws.com] has left #shogun []11:12
-!- nube [~rho@116.90.239.3] has quit [Quit: Leaving.]11:17
-!- nube [~rho@116.90.239.3] has joined #shogun11:17
-!- lambday [3ba2174f@gateway/web/freenode/ip.59.162.23.79] has quit []11:22
@lisitsynsijin: good point, making these checks lazy is on my todo11:29
-!- deerishi [73f88294@gateway/web/freenode/ip.115.248.130.148] has joined #shogun11:34
deerishi@sonny2k :i have resent the pr11:35
sijinlisitsyn: ok, currently, i just set num_neighbor of kpca to some "safe" value. btw, my pr still fails in travis-build ( I have pulled the latest develop branch)11:38
-!- deerishi [73f88294@gateway/web/freenode/ip.115.248.130.148] has quit [Ping timeout: 245 seconds]11:41
-!- van51 [~van51@athedsl-320452.home.otenet.gr] has left #shogun ["PING 1368094192"]12:09
-!- nube [~rho@116.90.239.3] has quit [Ping timeout: 256 seconds]12:19
shogun-notifier-shogun: deerishi :develop * b0a4260 / examples/ (4 files): https://github.com/shogun-toolbox/shogun/commit/b0a4260edf0bfd7ae451aaf15bb31e19ec72d62312:22
shogun-notifier-shogun: kpca12:22
shogun-notifier-shogun: Soeren Sonnenburg :develop * 372889d / examples/ (4 files): https://github.com/shogun-toolbox/shogun/commit/372889d49545994b1ae4f98bbaa01a1ed50b785e12:22
shogun-notifier-shogun: Merge pull request #1078 from deerishi/mk112:22
shogun-notifier-shogun:12:22
shogun-notifier-shogun: Kernel PCA Test/Check12:22
shogun-buildbotbuild #938 of bsd1 - libshogun is complete: Failure [failed configure]  Build details are at http://www.shogun-toolbox.org/buildbot/builders/bsd1%20-%20libshogun/builds/938  blamelist: deerishi <deerishi@gmail.com>12:29
shogun-notifier-shogun: Viktor Gal :feature/PRNG * 801bb93 / src/configure,src/shogun/mathematics/Random.cpp: https://github.com/shogun-toolbox/shogun/commit/801bb935307de36df78abd37d881e8429fdb573c12:36
shogun-notifier-shogun: Random use d/SFMT fill array functions only when memory is aligned12:36
-!- mdragan [8d55007a@gateway/web/freenode/ip.141.85.0.122] has quit [Ping timeout: 245 seconds]12:39
-!- travis-ci [~travis-ci@ec2-107-20-28-143.compute-1.amazonaws.com] has joined #shogun12:40
travis-ci[travis-ci] it's Soeren Sonnenburg'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/701647412:40
-!- travis-ci [~travis-ci@ec2-107-20-28-143.compute-1.amazonaws.com] has left #shogun []12:40
@wikingsonney2k: once somebody has the time, should implement memory alignment support in shogun :P12:41
@sonney2kwiking, but this has some side effects no?12:42
@sonney2kif we allocate lots of small chunks12:42
@sonney2k?12:42
@wikingsonney2k: well it has a sideeffect of course12:43
@wikingoverhead12:43
shogun-buildbotbuild #939 of bsd1 - libshogun is complete: Success [build successful]  Build details are at http://www.shogun-toolbox.org/buildbot/builders/bsd1%20-%20libshogun/builds/93912:43
@wikingsonney2k: i'm just saying that SFMT can only fast fill array with sse2 instructions if the memory is 16byte aligned12:43
@wikingobviously12:43
@wikingso i had to make a check there12:43
@wikingas in darwin malloc is already giving you back a 16 byte aligned memory12:44
@wikingalways12:44
@wikingon other os of course it's not like this12:44
shogun-buildbotbuild #773 of cyg1 - libshogun is complete: Failure [failed configure]  Build details are at http://www.shogun-toolbox.org/buildbot/builders/cyg1%20-%20libshogun/builds/773  blamelist: Soeren Sonnenburg <sonne@debian.org>12:44
@wikingsonney2k: but maybe we should as well add support for non system memory managers12:45
@wikinglike jmalloc12:45
@wikingi've prepared a patch for it12:45
@wikingi just wonder where the fuck did i put that one :DD12:45
@wikingi guess it's either a branch or in a stash12:45
@wikingyeah i think i got it :)12:45
@wikinganyhow the PRNG feature is about to be ready12:46
@wikingjemalloc and hoard is much faster12:47
@wikingthen the usual gnu malloc on linux12:47
@wikingsonney2k: http://www.hoard.org/12:49
@wikinghttp://plasma.cs.umass.edu/emery/screenshots12:49
@sonney2kwiking, speed is always welcome ... aligned_alloc()12:49
@wikingsonney2k: yeah so i'll push that configure patch for replacing the default system malloc12:50
@wikingi just need to test them12:50
@wikingbut this prng should be finished as well12:51
@sonney2kwiking, one thing at a time12:51
@wikingyeah tell me about it12:51
-!- deerishi [73f88294@gateway/web/freenode/ip.115.248.130.148] has joined #shogun12:52
@sonney2kwiking, if you do this with aligned_alloc - we need to tell gcc somehow that the memory is aligned12:52
@sonney2kotherwise it won't fully benefit from it12:52
@wikingsonney2k: posix_memalign12:52
@wikingwe should use that rather12:52
@wikingbtw how we should test the new PRNG?12:53
@wikingi mean now i think it's there12:53
@wikingit's ready12:53
@wikingbut we need to fix the integration tests12:53
@wiking../data/clustering/KMeans_EuclidianDistance_3.mERROR12:54
@wikinglibshogun (x86_64/git_801bb93_2013-05-09_12:36134331283) Copyright (C) 1999-2009 Fraunhofer Institute FIRST Copyright (C) 1999-2011 Max Planck Society Copyright (C) 2009-2011 Berlin Institute of Technology Copyright (C) 2012 Soeren Sonnenburg, Sergey Lisitsyn, Heiko Strathmann Written (W) 1999-2012 Soeren Sonnenburg, Gunnar Raetsch et al. ( configure options: "configure options --disable-optimization --interfaces=python_static" compile flags: "-fPIC -g 12:54
@wikingas u can see this fails already12:54
@sonney2kwiking, yeah makes sense12:54
@sonney2kk-means does random init12:54
@wikingyep12:54
@wikingi know12:54
@wikingbut we need to fix that12:54
@wikingand as well other integration tests12:54
@sonney2kwell once you have unit tests we can just regenerate the expected data12:54
@wikingunit tests?12:54
@wikingthey are done :)12:54
@wikinghttps://travis-ci.org/shogun-toolbox/shogun/jobs/701670012:55
deerishifinally merged 1 PR!!!!!!!!!!!!!!12:55
deerishifeels gr8!!!12:55
@wikingdeerishi: yeah tell me about it12:55
@wikingdeerishi: my mailbox is full with your PR attempts ;P12:55
deerishihaha12:56
-!- travis-ci [~travis-ci@ec2-23-22-231-136.compute-1.amazonaws.com] has joined #shogun12:56
travis-ci[travis-ci] it's Viktor Gal'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/701669812:56
-!- travis-ci [~travis-ci@ec2-23-22-231-136.compute-1.amazonaws.com] has left #shogun []12:56
deerishiwill start working on global alignment kernels12:56
deerishithat issue is still open rite?12:58
shogun-buildbotbuild #1070 of deb3 - modular_interfaces is complete: Failure [failed test python_modular]  Build details are at http://www.shogun-toolbox.org/buildbot/builders/deb3%20-%20modular_interfaces/builds/1070  blamelist: deerishi <deerishi@gmail.com>13:05
@wikingsonney2k: so, merge?13:09
-!- deerishi [73f88294@gateway/web/freenode/ip.115.248.130.148] has quit [Ping timeout: 245 seconds]13:12
shogun-buildbotbuild #1071 of deb3 - modular_interfaces is complete: Failure [failed compile csharp_modular]  Build details are at http://www.shogun-toolbox.org/buildbot/builders/deb3%20-%20modular_interfaces/builds/1071  blamelist: Soeren Sonnenburg <sonne@debian.org>13:14
shogun-notifier-shogun: Viktor Gal :develop * c521a6d / .gitignore: https://github.com/shogun-toolbox/shogun/commit/c521a6d96b8abae3294aa45e98d0dc4a5007cf8813:20
shogun-notifier-shogun: Add .DS_Store to gitignore13:20
shogun-buildbotbuild #774 of cyg1 - libshogun is complete: Failure [failed configure]  Build details are at http://www.shogun-toolbox.org/buildbot/builders/cyg1%20-%20libshogun/builds/774  blamelist: Viktor Gal <viktor.gal@maeth.com>13:32
-!- travis-ci [~travis-ci@ec2-23-22-231-136.compute-1.amazonaws.com] has joined #shogun13:38
travis-ci[travis-ci] it's Viktor Gal'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/701747213:38
-!- travis-ci [~travis-ci@ec2-23-22-231-136.compute-1.amazonaws.com] has left #shogun []13:38
-!- foulwall [~foulwall@li379-21.members.linode.com] has joined #shogun13:52
shogun-buildbotbuild #1072 of deb3 - modular_interfaces is complete: Failure [failed compile csharp_modular]  Build details are at http://www.shogun-toolbox.org/buildbot/builders/deb3%20-%20modular_interfaces/builds/1072  blamelist: Viktor Gal <viktor.gal@maeth.com>13:57
@sonney2kwiking, yeah once the current errors are fixed14:36
@sonney2khmmhh MCLDA cannot work14:36
@sonney2kpickle27, didn't you do MCLDA :D14:37
@sonney2klook at multiclass/MCLDA.cpp:28214:37
@wikingok fix it fuck14:52
@wiking:>14:52
@wikingwho broke it? :)14:53
-!- lambday [3ba21749@gateway/web/freenode/ip.59.162.23.73] has joined #shogun15:01
lambdayhi HeikoS15:04
lambdayhello lisitsyn15:04
-!- abinash [75c8e12e@gateway/web/freenode/ip.117.200.225.46] has joined #shogun15:40
-!- vgorbati [d4029f22@gateway/web/freenode/ip.212.2.159.34] has joined #shogun15:46
-!- foulwall [~foulwall@li379-21.members.linode.com] has quit [Remote host closed the connection]15:58
-!- abinash [75c8e12e@gateway/web/freenode/ip.117.200.225.46] has quit [Ping timeout: 245 seconds]15:58
-!- votjakovr [~votjakovr@host-46-241-3-209.bbcustomer.zsttk.net] has joined #shogun16:09
-!- shogun-notifier- [~irker@7nn.de] has quit [Quit: transmission timeout]16:20
@wikingvotjakovr: ping16:38
-!- lambday [3ba21749@gateway/web/freenode/ip.59.162.23.73] has quit []16:38
votjakovrwiking: Hi16:39
@wikinglisitsyn: ping16:40
@wikingvotjakovr: with one of your commit we've got some things broken16:40
@wikingi mean tests16:40
votjakovrwiking: Do you mean travis-ci fault?16:41
@wikingvotjakovr: yes16:42
@wikingvotjakovr: suddenly gaussian regression started to fail16:42
@wikingas well as charp modular cannot be compiled16:42
@wikinglisitsyn: do you know what's DSYEV failed with code 175 is?16:45
votjakovrwiking: but on my machine gaussian regression test is OK16:45
@wikingi mean what is actually error code 17516:45
@wikingvotjakovr: not on travis16:45
@wikingvotjakovr: what's your machine btw16:45
votjakovrwiking: intel core i7-860, Ubuntu 13.0416:46
@wikingmmmhm16:46
@wikingand when u run make tests16:46
@wikingthe python gaussian regression runs fine16:46
votjakovrwiking: I run tester.py and it is OK16:47
@wikingvotjakovr: in shogun/src16:48
@wikingjust type make tests16:48
votjakovrwiking: It is failed on classifier_svmlight_string_features_precomputed_kernel and library_map libshogun examples16:51
-!- gsomix [~gsomix@188.168.3.6] has quit [Remote host closed the connection]16:52
@wikingmmm interesting16:54
votjakovrwiking: And it stops on libshogun examples, that is why I run tester.py16:55
@wikingvotjakovr: well then obviously there's more problem16:56
votjakovrwiking: these libshogun examples reports: undefined reference to symbol 'pthread_spin_init@@GLIBC_2.2.5'16:57
@wikingaaaah16:57
@wikingvotjakovr: can u check configure.log16:58
@wikingif u still have it16:58
@wikingif not then run again ./congiure16:58
@wikingand check configure.log for: spinlock16:58
@wikingdamn fuck.... i have to fix that :)16:59
votjakovrwiking: 'Result is: yes'17:01
@wikingvotjakovr: yeah i figured17:01
@wikingthere's some linking problem there17:02
@wikingas u supposed to have spinlock17:02
@wikingin configure.log17:02
@wikingwhat is the cc line?17:02
@wikingsonney2k: darwin version of spinlock: http://developer.apple.com/library/mac/#documentation/Darwin/Reference/ManPages/man3/spinlock.3.html17:04
votjakovrcc   -I/usr/include/json   -I/usr/include/libxml2   -I/usr/include/atlas -isystem /usr/include/eigen3   -fPIC  -g -Wall -Werror-implicit-function-declaration -Wno-unused-parameter -Wformat -Wformat-security -Wparentheses -Wshadow -Wno-unknown-pragmas -Wno-deprecated -O9 -fexpensive-optimizations -frerun-cse-after-loop -fcse-follow-jumps -finline-functions -fschedule-insns2 -fthread-jumps -fforce-addr -fstrength-reduce -funroll17:05
votjakovr-loops -mfpmath=sse -march=native -mtune=native -pthread ./configure-25615-10652.c -o ./configure-2697-10652.o  -Xlinker --no-undefined -pthread -lm -pthread -lhdf5 -ljson -lxml2 -llapack -lcblas -llapack_atlas -larpack -lnlopt -lglpk -lm -llzo2 -lsnappy -lz -lbz2 -llzma17:05
pickle27sonney2k: oh god17:06
votjakovrwiking: It is from spinlock checking section17:06
@wikingvotjakovr: yep17:06
pickle27sonney2k: what a terrible mistake my bad17:06
@wikingvotjakovr: i wonder why you get undefined reference to symbol 'pthread_spin_init@@GLIBC_2.2.5'17:06
@wikingsince with these flags you managed to compile that small example and actually call pthread_spin_init17:07
votjakovrwiking: libshogun example also writes this: 'note: 'pthread_create@@GLIBC_2.2.5' is defined in DSO /lib/x86_64-linux-gnu/libpthread.so.0 so try adding it to the linker command line'17:08
votjakovrwiking: and this: 'note: 'pthread_spin_init@@GLIBC_2.2.5' is defined in DSO /lib/x86_64-linux-gnu/libpthread.so.0 so try adding it to the linker command line'17:09
@wikingaaahaaa17:10
@wikingi wonder what is linked then17:10
pickle27sonney2k: sent a PR to fix that embarrassing mistake, I'll be looking into breaking up the train function, making a unit test and an Eigen3 version over the next bit17:12
votjakovrwiking: Btw csharp_modular is OK on my last PR.17:19
-!- foulwall [~foulwall@2001:da8:215:c252:d0e6:bc9e:72f:96d9] has joined #shogun17:26
votjakovrwiking: When I added -lpthread and -L/lib/x86_64-linux-gnu options, these two examples was linked without errors.17:51
@lisitsynwiking: hey back17:51
@lisitsynhey, back I mean17:51
@lisitsyndsyev 175 probably means17:51
@lisitsynthat 175th leading minor has negative det17:52
@lisitsynahh no17:52
@lisitsynit is tridiagonalization error17:52
@lisitsynwiking: I guess it may happen if matrix is not symmetric17:53
@wikinglisitsyn: any suggestions? :)17:54
@wikinglisitsyn: i mean now with using PruneVarSubMean finally MulticlassLibLinear started to give me reasonable results17:54
@lisitsynwiking: assure it is symmetric17:54
@lisitsynlet me get back to log17:54
@lisitsynwhere does it happen?17:54
@wikinglisitsyn: well i load in the data17:54
@wikingi mean data matrix -> realfeatures17:55
@wikingand then i try to do the pca17:55
@wikingthen basically crashes with that assert17:55
@lisitsynohh interesting17:55
@lisitsynwiking: http://starlogs.net/#shogun-toolbox/shogun17:57
pickle27starlogs is awesome!17:57
@lisitsynhaha17:57
@lisitsynI've never seen it before17:58
pickle27there is also http://www.commitlogsfromlastnight.com/17:58
@wikinglisitsyn: hahaha17:59
-!- foulwall [~foulwall@2001:da8:215:c252:d0e6:bc9e:72f:96d9] has quit [Remote host closed the connection]18:23
-!- deerishi [73f88294@gateway/web/freenode/ip.115.248.130.148] has joined #shogun18:53
@lisitsynHeikoS: why clusters?18:55
@lisitsynI don't get your comment here :)18:55
@lisitsynabout KNN and modsel18:55
@HeikoSuh18:55
@HeikoSwait18:55
@HeikoSwasnt that KMeans? :)18:55
@HeikoSdamn18:55
@HeikoSI always switch those18:55
@HeikoSlet me delete the comment quickly18:55
@lisitsynhaha!18:56
@lisitsynI thought so18:56
@lisitsynHeikoS: I think the idea on that issue is that we just can compute nearest neighbors once for maximum K18:56
@HeikoSlisitsyn: sorry :)18:56
@lisitsynand later we are much faster with doing classification18:56
@HeikoSlisitsyn: explain18:57
@lisitsynHeikoS: if we computed neighbors in train set for test set18:57
@lisitsynwith K set to maximum of some range18:57
@lisitsynwe can do classification rather fast - we just select precomputed indices18:57
@lisitsynwe can even go with binary search here18:58
@HeikoSlisitsyn: I cannot find the issue18:58
@HeikoShow to search issues18:58
@HeikoSlisitsyn:  I see18:58
@lisitsynHeikoS: https://github.com/shogun-toolbox/shogun/issues/46818:59
@HeikoSbut who cares about knn?18:59
@lisitsynhaha18:59
@lisitsyngood question18:59
@HeikoSgood idea still18:59
@HeikoSbut not really relevant for anyone18:59
@HeikoSah, long day here :)19:01
@HeikoSlisitsyn: currently working on something for NIPS. And the title is MCMC Hammer :D19:01
@lisitsynHeikoS: ha! I have holiday today :P19:01
@lisitsynhahahahaha19:01
@lisitsynyou can't touch this19:01
@HeikoSexactly :D19:01
@lisitsyntadatada19:02
@lisitsynyou can't touch this19:02
@HeikoSwill be the best sampler ever19:02
@lisitsyncan't touch this19:02
@HeikoSlisitsyn:  do you know the original19:02
@HeikoSI like that even more19:02
@HeikoSrick james - superfreak19:02
@lisitsynsuperfreak superfreak!19:03
@lisitsynshe's superfreaky19:03
@lisitsyncan't touch this!19:04
@HeikoShaha :)19:04
@lisitsynHeikoS: my mind is in off state now19:04
@lisitsynwiking: u can't touch this!19:04
@lisitsynHeikoS: can't touch this markov chain19:05
@lisitsynI can't touch shogun19:06
@HeikoShehe, glad you like this :)19:07
@lisitsynHeikoS: u can't touch this paper19:07
@HeikoSgrove on blackburn!19:07
@lisitsynHeikoS: you may say that to your supervisor19:08
@lisitsynu can't touch this19:08
@lisitsyn:D19:08
votjakovrwiking: So what do you think about how to solve the problem with libshogun examples?19:10
@lisitsynvotjakovr: u can't touch this!19:10
@lisitsyn:D19:10
votjakovrlisitsyn: Yeah :D19:11
@lisitsynHeikoS: ooh why oh why you did it to me19:11
@lisitsynMCMC Hammer rocks19:11
votjakovrlisitsyn: great song!19:12
@HeikoSjust being evil :)19:12
@lisitsynvotjakovr: you get it!19:12
@HeikoShttps://www.youtube.com/watch?v=Vv3f0QNWvWQ&feature=player_embedded19:13
@lisitsynHeikoS: hahaha19:13
@lisitsynHeikoS: btw give me any good reference on mcmc bitte schoen!19:16
@HeikoSlisitsyn: like a tutorial?19:16
@lisitsynyes for an asshole like me19:16
@lisitsyn:D19:16
@HeikoShttps://www.google.co.uk/url?sa=t&rct=j&q=&esrc=s&source=web&cd=2&ved=0CDwQFjAB&url=http%3A%2F%2Fwww.people.fas.harvard.edu%2F~plam%2Fteaching%2Fmethods%2Fmcmc%2Fmcmc.pdf&ei=FNqLUeG4M6X40gWlwoGADw&usg=AFQjCNE13QZ-k-KHSmw_NiHzAB9Gf4hOzA&sig2=FOlbrgLY6HNNe1fdrXf8WQ&bvm=bv.46340616,d.d2k19:17
@HeikoSI like this19:17
@lisitsynnice, thanks!19:17
vgorbatilisitsyn: hi, I wanted to ask: you are creating DenseMatrix from FeatureCallback 2 times, and I also need to do this in manifold sculpting implementation - do you mind if I will extract these lines into a separate function?19:18
@lisitsynvgorbati: hmm where it is created 2 times?19:19
vgorbatilisitsyn: I mean that there are 2 places where you do this - in embedPassThru and in embed for t-SNE19:19
@lisitsynahh19:20
@lisitsynyes of course19:20
@lisitsynif you need it19:20
@lisitsynvgorbati: just for better understanding19:20
@lisitsynidea of using callbacks here is to give some flexibility19:20
vgorbatilisitsyn: I am thinking to put it in utils/matrix.hpp, is it a reasonable place?19:20
@lisitsynvgorbati: no I think some other place would be better19:21
@lisitsynmatrix.hpp has center thing19:21
@lisitsynit has nothing to do with callbacks19:21
@lisitsynsome utils/features.hpp may be or so19:22
vgorbatilisitsyn: ok. btw, I see centerMatrix calls in tapkee/routines/pca.hpp or tapkee/tapkee_methods.hpp, but there are no #include '.../utils/matrix.hpp' there - should it be so?19:24
votjakovrHeikoS: Hi, I'd like to discuss something. Do you have any time?19:26
@HeikoSvotjakovr: sure, whats up?19:27
@lisitsynvgorbati: yeah they are just in the same compilation unit so it works19:28
@lisitsynbut it should be here probably, yes19:28
@HeikoSvotjakovr:  will be leaving work soon though, whats up?19:30
votjakovrHeikoS: I'm not sure, but I think that there is a bug in GPML matlab toolbox in partial derivative by ell in covSEiso. It is computed like: dK(i,j)/dell = sf2 * exp(-(x(i) - x(j))^2/(2*ell^2)) * (x(i) - x(j))^2 / (ell^2), but I think it should be computed like:  dK(i,j)/dell = sf2 * exp(-(x(i) - x(j))^2/(2*ell^2)) * (x(i) - x(j))^2 / (ell^*3*). What do you think about this?19:32
-!- vgorbati [d4029f22@gateway/web/freenode/ip.212.2.159.34] has quit [Ping timeout: 245 seconds]19:32
@HeikoSvotjakovr: let me check19:36
@HeikoSvotjakovr: whats the kernel itself? the functional form?19:38
votjakovrHeikoS: K(i, j) = sf2 * exp(-(x(i) - x(j))^2/(2*ell^2))19:40
@HeikoSvotjakovr: so the difference is the exponent in the ell right?19:43
votjakovrHeikoS: yep19:43
@HeikoSvotjakovr: wow and in the GPML toolbox, there is a two, should be a bug then. I wonder why nobody discovered this so far19:43
@HeikoSwhich file is it computed in?19:44
votjakovrHeikoS: cov/covSEiso.m19:44
@HeikoSand i is19:45
@HeikoSthe parmeter index of which the partial derivative should be computed?19:45
votjakovrfirst19:45
@HeikoSK = sf2*exp(-K/2).*K;19:45
votjakovryep19:46
@HeikoSyou could do a quick simple check:19:46
@HeikoSplot the kernel for two fixed points as a 1D function of ell19:47
@HeikoSand plot the derivative19:47
@HeikoSseems weird that this bug is in there ...19:47
@HeikoSvotjakovr: wait19:49
@HeikoSah sorry19:50
@HeikoSno I think its a bug, but make sure to plot it19:50
votjakovrHeikoS: I think the same19:50
@HeikoSif it doesnt make sense (and your correction K = sf2*exp(-K/2).*K/ell; makes sense), then we should report it19:51
@HeikoSthe same?19:51
@HeikoSah I see19:51
votjakovrYep, I think it should be computed like K = sf2*exp(-K/2).*K/ell19:52
@HeikoSindeed19:52
@HeikoScould you send me the plots of both versions once you created them? I am curious how the difference looks like. Also good for reporting the bug19:52
@HeikoSso I guess the line was copied in shogun? :)19:53
-!- deerishi [73f88294@gateway/web/freenode/ip.115.248.130.148] has quit [Ping timeout: 245 seconds]19:54
votjakovrWhich line?19:54
@HeikoSthe kernel derivative19:55
votjakovrSo in shogun kernel derivative is computed by width = 2*ell^2 and computed correctly19:56
-!- FSCV [~FSCV@204.45.132.11] has joined #shogun19:56
@HeikoSokay19:56
@HeikoSvotjakovr: well, nice job that you spotted this! :)19:57
votjakovrHeikoS: I mean in CGaussianKernel19:57
@HeikoSvotjakovr: ok saw it19:58
@HeikoSvotjakovr: so maybe you should implement a graphical example which selects the best kernel?19:59
@HeikoSyou could generate data from the GP with a known kernel size and then learn the kernel size via ML219:59
@HeikoSand then plot things in python19:59
@HeikoSthis way we have 1) a nice example for modelselection with GP regression 2) evidence that things work out fine in shogun19:59
@HeikoShow did you spot the bug btw?20:00
@HeikoSwhen writing unit tests?20:00
@HeikoScomparing against GPML?20:00
votjakovrHeikoS: Yep :)20:00
@HeikoSvery cool that you do that! Otherwise we can never be sure whether things work. And even finding bugs in toolboxes that are referenced by thousands of people around the world. Awesome! :)20:01
@HeikoSvotjakovr: I gotta go home now, see you around!20:01
votjakovrHeikoS: Thanks :)20:01
@HeikoSbye!20:02
votjakovrSee you soon20:02
-!- van51 [~van51@athedsl-320452.home.otenet.gr] has joined #shogun20:05
@sonney2kvan51, could you please fix the build warning and split up your combine_kernels function into a couple of reasonable sub-functions?20:37
@sonney2kthe function is just to big to be parse-able20:37
@sonney2kvan51, this one here http://shogun-toolbox.org/buildbot/builders/deb3%20-%20modular_interfaces/builds/1072/steps/compile%20libshogun/logs/warnings%20%282%2920:39
-!- shogun-notifier- [~irker@7nn.de] has joined #shogun20:44
shogun-notifier-shogun: Soeren Sonnenburg :develop * 874f3f3 / src/shogun/multiclass/MCLDA.cpp: https://github.com/shogun-toolbox/shogun/commit/874f3f3d5cae12df993e84249129707f924bedb320:44
shogun-notifier-shogun: MCLDA fixed covariance matrix normalization20:44
van51sonney2k: yea sure20:48
@sonney2kvotjakovr, you said it you fixed the c# issue already?20:48
@sonney2kvan51, thanks20:48
@sonney2kwiking, whats up with the spinlock thing?20:48
van51soneey2k: btw as I am re-writing the CCombinedKernel to use CDynamicObjectArray, should I also change this function to return an array?20:49
van51or it doesn't matter?20:49
van51sonney2k*20:49
@sonney2kvan51, well yes but one step at a time?20:51
@sonney2klisitsyn, we need that spreadsheet20:51
votjakovrsonney2k: nope, i said that my PR, it seems, didn't break c# modular compilation.20:52
@sonney2kvotjakovr, ok then let me do the fix20:52
@sonney2kwiking, you want some defines for spinlock business & OSX?20:53
shogun-buildbotbuild #775 of cyg1 - libshogun is complete: Failure [failed configure]  Build details are at http://www.shogun-toolbox.org/buildbot/builders/cyg1%20-%20libshogun/builds/775  blamelist: Soeren Sonnenburg <sonne@debian.org>20:57
votjakovrsonney2k: Ok, i'd like to ask about failed integration tests in travis-ci. How do you think to fix this problem?21:04
-!- travis-ci [~travis-ci@ec2-107-20-28-143.compute-1.amazonaws.com] has joined #shogun21:05
travis-ci[travis-ci] it's Soeren Sonnenburg'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/703003621:05
-!- travis-ci [~travis-ci@ec2-107-20-28-143.compute-1.amazonaws.com] has left #shogun []21:05
shogun-notifier-shogun: Soeren Sonnenburg :develop * 7418ae1 / src/interfaces/modular/modshogun_ignores.i: https://github.com/shogun-toolbox/shogun/commit/7418ae1b6acd86203d958ec2ff0a960f2f6d646021:06
shogun-notifier-shogun: fix c# build failure21:06
@sonney2kvotjakovr, which one?21:06
votjakovrsonney2k: gp regression tests21:07
-!- gsomix [~Miranda@188.168.3.6] has joined #shogun21:07
gsomixgood evening21:08
shogun-buildbotbuild #776 of cyg1 - libshogun is complete: Failure [failed configure]  Build details are at http://www.shogun-toolbox.org/buildbot/builders/cyg1%20-%20libshogun/builds/776  blamelist: Soeren Sonnenburg <sonne@debian.org>21:09
votjakovrsonney2k: I think, it works everywhere except travis21:09
@lisitsynHeikoS: sonney2k: please check the doc I shared21:14
shogun-buildbotbuild #1073 of deb3 - modular_interfaces is complete: Failure [failed compile csharp_modular]  Build details are at http://www.shogun-toolbox.org/buildbot/builders/deb3%20-%20modular_interfaces/builds/1073  blamelist: Soeren Sonnenburg <sonne@debian.org>21:21
-!- travis-ci [~travis-ci@ec2-107-20-28-143.compute-1.amazonaws.com] has joined #shogun21:28
travis-ci[travis-ci] it's Soeren Sonnenburg'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/703071921:28
-!- travis-ci [~travis-ci@ec2-107-20-28-143.compute-1.amazonaws.com] has left #shogun []21:28
@sonney2kvotjakovr, I don't know either - travis is just some buildbot running some ubuntu virtual machine it seems21:43
shogun-buildbotbuild #1074 of deb3 - modular_interfaces is complete: Failure [failed test python_modular]  Build details are at http://www.shogun-toolbox.org/buildbot/builders/deb3%20-%20modular_interfaces/builds/1074  blamelist: Soeren Sonnenburg <sonne@debian.org>21:46
@sonney2kHuh?!21:49
@sonney2kwhat is that21:49
@sonney2kThe following tests failed!21:49
@sonney2kp21:49
@sonney2kp ???21:50
@lisitsynwhat?21:50
@sonney2khttp://www.shogun-toolbox.org/buildbot/builders/deb3%20-%20modular_interfaces/builds/1074/steps/test%20python_modular/logs/stdio21:50
@lisitsynsonney2k: I see no p in examples21:51
@lisitsynsonney2k: so how did that happen :D21:56
@sonney2kno idea yet21:58
-!- votjakovr [~votjakovr@host-46-241-3-209.bbcustomer.zsttk.net] has quit [Quit: Leaving]21:58
-!- arcolife [arcolife@nat/redhat/x-tfkofwlsgeocvlqk] has joined #shogun22:06
-!- iglesiasg [d58f329b@gateway/web/freenode/ip.213.143.50.155] has joined #shogun22:10
-!- mode/#shogun [+o iglesiasg] by ChanServ22:11
shogun-notifier-shogun: Soeren Sonnenburg :develop * b12a2f1 / data: https://github.com/shogun-toolbox/shogun/commit/b12a2f1a57eaac68ecde3f449cfaa7bb8641202822:17
shogun-notifier-shogun: require new data version for kpca tests22:17
@sonney2klisitsyn, reason is kpca data not yet there and whatever mishandling in tester.py22:18
@lisitsynoh I see22:18
@sonney2klisitsyn, btw why do we have 2 kernelpca things?22:21
@sonney2kpreprocessor_kernelpca_modular.py22:21
@sonney2kpreprocessor_kpca.py ?22:21
@lisitsynwhat is preprocessor_kpca ..22:23
@lisitsyn:D22:23
@lisitsynuh what a code22:23
shogun-notifier-shogun: Soeren Sonnenburg :develop * f313ed6 / tests/integration/python_modular/tester.py: https://github.com/shogun-toolbox/shogun/commit/f313ed636e5707dacefb130fde2924c2d2272f4022:23
shogun-notifier-shogun: fix weird bug in tester.py occurring when no data is available22:23
@lisitsynsonney2k: it is you who merged it :D22:24
@lisitsynsonney2k: but you were under PR DoS attack22:24
@sonney2kpsst22:24
@sonney2kdon't tell anyone22:24
@lisitsynlet me count22:24
shogun-buildbotbuild #777 of cyg1 - libshogun is complete: Failure [failed configure]  Build details are at http://www.shogun-toolbox.org/buildbot/builders/cyg1%20-%20libshogun/builds/777  blamelist: Soeren Sonnenburg <sonne@debian.org>22:24
@lisitsynsonney2k: that guy sent you 13 pull requests22:25
@lisitsynno surprise you got confused22:25
@lisitsyn:D22:25
@sonney2klisitsyn, do we have some more nice graphical examples now btw?22:25
@lisitsynsonney2k: yes of course22:25
@lisitsynsonney2k: graphical/inverse_covariance_estimation_demo.py22:26
@sonney2kwho did that?22:27
@lisitsynsonney2k: monica22:27
@lisitsynsonney2k: graphical/group_lasso.py22:27
@lisitsynsonney2k: that's cesar fuentes22:28
@sonney2klooks very cool22:28
@sonney2kand very short too!22:29
-!- arcolife [arcolife@nat/redhat/x-tfkofwlsgeocvlqk] has left #shogun ["Leaving"]22:30
@wikingfuck22:33
@wikingthat pr spammed my inbox!22:33
@lisitsynwiking: kpca?22:33
@wikingy22:34
@wikingokok22:34
@wikingwhen can i merge?22:34
@lisitsynwiking: merge what?22:34
@wikingprng branch22:34
@wikingimo it's ready22:35
@lisitsynah22:35
@wikingif i see kpca one more time i'll fucking git rm it :D22:35
@lisitsynwiking: well it is just 13 attempts22:35
@wikinghehehe22:35
@wikingonly22:35
@wiking:D22:35
@lisitsynwhy so serious22:35
@wikingwell to be totally22:35
@wikinghonest22:35
@wikingthe PRNG branch is like 20+ commits22:36
@wiking:DDDD22:36
@wikingso it's even worse than that kpca PR attempt22:36
@lisitsynno, why?22:36
@wikingtoo many commit :P22:36
@wikinganyhow22:36
@wikingwhen do we get develop branch into a working shape again?22:36
@lisitsynwhy not, if they are not breakers22:36
@sonney2kwiking, I think I fixed all issues...22:37
@sonney2kbut lets wait for the BB22:37
@wikingok22:37
@wikingsonney2k: if it goes OK22:37
@wikingthen let's merge prng22:37
@wikingsonney2k: btw why spinlock is more preferred than simple mutex?22:38
@sonney2klisitsyn, what is an inverse covariance matrix btw?22:38
@sonney2kwiking, faster!22:39
@lisitsynsonney2k: just inverse of covariance matrix22:39
@wikingok sonney2k i'm just reading wikipedia22:39
@sonney2kok what does a inverse covmatrix tell me?22:39
@sonney2kwiking, busy loops!22:39
@lisitsynsonney2k: how features are related22:39
-!- travis-ci [~travis-ci@ec2-107-20-28-143.compute-1.amazonaws.com] has joined #shogun22:39
travis-ci[travis-ci] it's Soeren Sonnenburg'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/703263922:39
-!- travis-ci [~travis-ci@ec2-107-20-28-143.compute-1.amazonaws.com] has left #shogun []22:39
@lisitsynsonney2k: lasso regularization pushes coefficients to zero22:40
@lisitsynso you get only strongly related features22:40
@sonney2kwiking, so for e.g. SG_UNREF / SGVector passing around we need these to ensure the refcount is in sane state22:40
@sonney2klisitsyn, ohh nice22:41
@sonney2know the example makes more sense to me22:41
@lisitsynsonney2k: I wrote it one day22:41
@lisitsynbut never had an example22:41
@lisitsynI just re-used some stuff from SLEP22:42
@lisitsynthat's why22:42
@lisitsyn:)22:42
@lisitsynsonney2k: group lasso is very cool too22:42
@lisitsynsonney2k: but this is something you understand already, yes?22:43
shogun-notifier-shogun: Soeren Sonnenburg :develop * 4a0582b / examples/undocumented/python_modular/graphical/inverse_covariance_estimation_demo.py: https://github.com/shogun-toolbox/shogun/commit/4a0582b9abce9743125a83e5cadcf389a8e59e6722:43
shogun-notifier-shogun: fix typo in inv cov estiamtion demo22:43
shogun-buildbotbuild #778 of cyg1 - libshogun is complete: Failure [failed configure]  Build details are at http://www.shogun-toolbox.org/buildbot/builders/cyg1%20-%20libshogun/builds/778  blamelist: Soeren Sonnenburg <sonne@debian.org>22:45
-!- van51 [~van51@athedsl-320452.home.otenet.gr] has quit [Quit: Leaving.]22:53
shogun-buildbotbuild #1075 of deb3 - modular_interfaces is complete: Success [build successful]  Build details are at http://www.shogun-toolbox.org/buildbot/builders/deb3%20-%20modular_interfaces/builds/107522:56
-!- travis-ci [~travis-ci@ec2-107-20-28-143.compute-1.amazonaws.com] has joined #shogun22:57
travis-ci[travis-ci] it's Soeren Sonnenburg'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/703287822:57
-!- travis-ci [~travis-ci@ec2-107-20-28-143.compute-1.amazonaws.com] has left #shogun []22:57
@sonney2kwiking, it's your turn23:04
@sonney2kwiking, buildbot is happy23:04
@sonney2klisitsyn, isn't group lasso just MKL?23:05
@lisitsynsonney2k: I can't cast it to MKL23:05
@lisitsynmay be it is but I don't know23:05
@lisitsynsonney2k: L1/L2 is like23:06
@lisitsynsum of absolute L2 in groups23:06
@lisitsynso weights in each feature group is pushed towards each other23:06
@lisitsynwhile groups are pushed to zero23:07
shogun-buildbotbuild #779 of cyg1 - libshogun is complete: Failure [failed configure]  Build details are at http://www.shogun-toolbox.org/buildbot/builders/cyg1%20-%20libshogun/builds/779  blamelist: Soeren Sonnenburg <sonne@debian.org>23:07
@sonney2kyeah same for MKL23:08
@sonney2kyou have SVM (L2) in group23:09
@sonney2kand L1 on top23:09
@sonney2kand it is crap :D23:09
@lisitsynsonney2k: ahh so you mean like kernels that work just on one group of features23:10
@lisitsynthis way yes23:10
@sonney2kyes23:10
@lisitsynsonney2k: I did one experiment for georg last summer23:11
@lisitsynhierarchical regularization worked quite well23:11
@lisitsynwell the data was hierarchical23:11
@lisitsynthat's why I guess23:11
-!- travis-ci [~travis-ci@ec2-54-224-131-101.compute-1.amazonaws.com] has joined #shogun23:13
travis-ci[travis-ci] it's Soeren Sonnenburg'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/703342023:13
-!- travis-ci [~travis-ci@ec2-54-224-131-101.compute-1.amazonaws.com] has left #shogun []23:13
@sonney2kwiking, alright once you wake up do your merge23:45
@iglesiasggood night guys23:47
-!- iglesiasg [d58f329b@gateway/web/freenode/ip.213.143.50.155] has quit [Quit: Page closed]23:50
shogun-buildbotbuild #1077 of deb3 - modular_interfaces is complete: Failure [failed test python_modular]  Build details are at http://www.shogun-toolbox.org/buildbot/builders/deb3%20-%20modular_interfaces/builds/1077  blamelist: Soeren Sonnenburg <sonne@debian.org>23:57
--- Log closed Fri May 10 00:00:38 2013
« Wednesday, 2013-05-08 Index Friday, 2013-05-10 »

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