{"id":203,"date":"2006-06-30T07:25:28","date_gmt":"2006-06-30T13:25:28","guid":{"rendered":"http:\/\/hunch.net\/?p=203"},"modified":"2006-06-30T08:52:31","modified_gmt":"2006-06-30T14:52:31","slug":"icml-papers","status":"publish","type":"post","link":"https:\/\/hunch.net\/?p=203","title":{"rendered":"ICML papers"},"content":{"rendered":"

Here are some ICML papers which interested me.<\/p>\n

    \n
  1. Arindam Banerjee<\/a> had a paper<\/a> which notes that PAC-Bayes bounds, a core theorem in online learning, and the optimality of Bayesian learning statements share a core inequality in their proof.<\/li>\n
  2. Pieter Abbeel<\/a>, Morgan Quigley<\/a> and Andrew Y. Ng<\/a> have a paper<\/a> discussing RL techniques for learning given a bad (but not too bad) model of the world.<\/li>\n
  3. Nina Balcan<\/a> and Avrim Blum<\/a> have a paper<\/a> which discusses how to learn given a similarity function rather than a kernel. A similarity function requires less structure than a kernel, implying that a learning algorithm using a similarity function might be applied in situations where no effective kernel is evident.<\/li>\n
  4. Nathan Ratliff<\/a>, Drew Bagnell<\/a>, and Marty Zinkevich<\/a> have a paper<\/a> describing an algorithm which attempts to fuse A*<\/sup> path planning with learning of transition costs based on human demonstration.<\/li>\n<\/ol>\n

    Papers (2), (3), and (4), all seem like an initial pass at solving interesting problems which push the domain in which learning is applicable.<\/p>\n

    I’d like to encourage discussion of what papers interested you and why. Maybe we’ll all learn a little bit, and it’s very likely that we all missed interesting papers in a multitrack conference.<\/p>\n","protected":false},"excerpt":{"rendered":"

    Here are some ICML papers which interested me. Arindam Banerjee had a paper which notes that PAC-Bayes bounds, a core theorem in online learning, and the optimality of Bayesian learning statements share a core inequality in their proof. Pieter Abbeel, Morgan Quigley and Andrew Y. Ng have a paper discussing RL techniques for learning given … <\/p>\n

    Continue reading “ICML papers”<\/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":[29,18],"tags":[],"class_list":["post-203","post","type-post","status-publish","format-standard","hentry","category-machine-learning","category-papers"],"_links":{"self":[{"href":"https:\/\/hunch.net\/index.php?rest_route=\/wp\/v2\/posts\/203","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=203"}],"version-history":[{"count":0,"href":"https:\/\/hunch.net\/index.php?rest_route=\/wp\/v2\/posts\/203\/revisions"}],"wp:attachment":[{"href":"https:\/\/hunch.net\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=203"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hunch.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=203"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hunch.net\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=203"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}