{"id":138,"date":"2005-11-02T23:08:53","date_gmt":"2005-11-03T05:08:53","guid":{"rendered":"http:\/\/hunch.net\/?p=138"},"modified":"2005-11-04T22:26:22","modified_gmt":"2005-11-05T04:26:22","slug":"progress-in-active-learning","status":"publish","type":"post","link":"https:\/\/hunch.net\/?p=138","title":{"rendered":"Progress in Active Learning"},"content":{"rendered":"

Several bits of progress have been made since Sanjoy<\/a> pointed out the significant lack of theoretical understanding of active learning<\/a>. This is an update on the progress I know of. As a refresher, active learning as meant here is:<\/p>\n

    \n
  1. There is a source of unlabeled data.<\/li>\n
  2. There is an oracle from which labels can be requested for unlabeled data produced by the source.<\/li>\n
  3. The goal is to perform well with minimal use of the oracle.<\/li>\n<\/ol>\n

    Here is what I’ve learned:<\/p>\n

      \n
    1. Sanjoy has developed sufficient and semi-necessary conditions for active learning given the assumptions of IID data and “realizability” (that one of the classifiers is a correct classifier).<\/li>\n
    2. Nina<\/a>, Alina<\/a>, and I developed an algorithm for active learning relying on only the assumption of IID data. A draft is here<\/a>.<\/li>\n
    3. Nicolo<\/a>, Claudio<\/a>, and Luca<\/a> showed that it is possible to do active learning in an entirely adversarial setting for linear threshold classifiers here<\/a>. This was published a year or two ago and I recently learned about it.<\/li>\n<\/ol>\n

      All of these results are relatively ‘rough’: they don’t necessarily make good algorithms as stated (although the last one has a few experiments). None of these results are directly comparable because the assumptions vary. Comparing the assumptions and the results leads to a number of remaining questions:<\/p>\n

        \n
      1. Do the sufficient and seminecessary conditions apply to the IID only case? The adversarial case?<\/li>\n
      2. Is there a generic algorithm for any hypothesis space that works in the fully adversarial setting?<\/li>\n
      3. What are special cases of these algorithms which are computationally tractable and useful?<\/li>\n<\/ol>\n

        The Foundations of Active Learning<\/a> workshop at NIPS should be a good place to discuss these questions.<\/p>\n","protected":false},"excerpt":{"rendered":"

        Several bits of progress have been made since Sanjoy pointed out the significant lack of theoretical understanding of active learning. This is an update on the progress I know of. As a refresher, active learning as meant here is: There is a source of unlabeled data. There is an oracle from which labels can be … <\/p>\n

        Continue reading “Progress in Active Learning”<\/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":[22,19],"tags":[],"class_list":["post-138","post","type-post","status-publish","format-standard","hentry","category-active","category-solutions"],"_links":{"self":[{"href":"https:\/\/hunch.net\/index.php?rest_route=\/wp\/v2\/posts\/138","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=138"}],"version-history":[{"count":0,"href":"https:\/\/hunch.net\/index.php?rest_route=\/wp\/v2\/posts\/138\/revisions"}],"wp:attachment":[{"href":"https:\/\/hunch.net\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=138"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hunch.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=138"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hunch.net\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=138"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}