{"id":2159,"date":"2011-12-13T19:17:35","date_gmt":"2011-12-14T01:17:35","guid":{"rendered":"http:\/\/hunch.net\/?p=2159"},"modified":"2011-12-13T19:17:35","modified_gmt":"2011-12-14T01:17:35","slug":"vowpal-wabbit-version-6-1-the-nips-tutorial","status":"publish","type":"post","link":"https:\/\/hunch.net\/?p=2159","title":{"rendered":"Vowpal Wabbit version 6.1 &#038; the NIPS tutorial"},"content":{"rendered":"<p>I just made <a href=\"https:\/\/github.com\/JohnLangford\/vowpal_wabbit\/zipball\/6.1\">version 6.1<\/a> of <a href=\"https:\/\/hunch.net\/~vw\/\">Vowpal Wabbit<\/a>.  Relative to <a href=\"https:\/\/hunch.net\/?p=1917\">6.0<\/a>, there are few new features, but many refinements. <\/p>\n<ol>\n<li>The cluster parallel learning code better supports multiple simultaneous runs, and other forms of parallelism have been mostly removed.  This incidentally significantly simplifies the learning core.<\/li>\n<li>The online learning algorithms are more general, with support for l<sub>1<\/sub> (via a truncated gradient variant) and l<sub>2<\/sub> regularization, and a generalized form of variable metric learning.<\/li>\n<li>There is a solid persistent server mode which can train online, as well as serve answers to many simultaneous queries, either in text or binary.<\/li>\n<\/ol>\n<p>This should be a very good release if you are just getting started, as we&#8217;ve made it compile more automatically out of the box, have several new <a href=\"https:\/\/github.com\/JohnLangford\/vowpal_wabbit\/wiki\/Examples\">examples<\/a> and updated documentation.<\/p>\n<p>As <a href=\"https:\/\/hunch.net\/?p=1594\">per<\/a> <a href=\"https:\/\/hunch.net\/?p=1068\">tradition<\/a>, we&#8217;re planning to do a tutorial at NIPS during the break at the <a href=\"http:\/\/biglearn.org\/index.php\/Schedule\">parallel learning workshop<\/a> at 2pm Spanish time Friday.  I&#8217;ll cover the basics, leaving the fun stuff for others.<\/p>\n<ol>\n<li><a href=\"http:\/\/www.cs.cmu.edu\/~mdudik\/\">Miro<\/a> will cover the <a href=\"http:\/\/en.wikipedia.org\/wiki\/L-BFGS\">L-BFGS<\/a> implementation, which he created from scratch.  We have found this works quite well amongst batch learning algorithms.<\/li>\n<li><a href=\"http:\/\/www.cs.berkeley.edu\/~alekh\/\">Alekh<\/a> will cover how to do <a href=\"https:\/\/hunch.net\/?p=2094\">cluster parallel learning<\/a>.  If you have access to a large cluster, VW is orders of magnitude faster than any other public learning system accomplishing linear prediction.  And if you are as impatient as I am, it is a real pleasure when the computers can keep up with you.<\/li>\n<\/ol>\n<p>This will be recorded, so it will hopefully be available for viewing online before too long.<\/p>\n<p>I hope to see you soon \ud83d\ude42<\/p>\n","protected":false},"excerpt":{"rendered":"<p>I just made version 6.1 of Vowpal Wabbit. Relative to 6.0, there are few new features, but many refinements. The cluster parallel learning code better supports multiple simultaneous runs, and other forms of parallelism have been mostly removed. This incidentally significantly simplifies the learning core. The online learning algorithms are more general, with support for &hellip; <\/p>\n<p class=\"link-more\"><a href=\"https:\/\/hunch.net\/?p=2159\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;Vowpal Wabbit version 6.1 &#038; the NIPS tutorial&#8221;<\/span><\/a><\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[4,42,29],"tags":[],"class_list":["post-2159","post","type-post","status-publish","format-standard","hentry","category-announcements","category-code","category-machine-learning"],"_links":{"self":[{"href":"https:\/\/hunch.net\/index.php?rest_route=\/wp\/v2\/posts\/2159","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/hunch.net\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/hunch.net\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/hunch.net\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/hunch.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=2159"}],"version-history":[{"count":0,"href":"https:\/\/hunch.net\/index.php?rest_route=\/wp\/v2\/posts\/2159\/revisions"}],"wp:attachment":[{"href":"https:\/\/hunch.net\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=2159"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hunch.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=2159"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hunch.net\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=2159"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}