{"id":155,"date":"2005-12-28T12:13:46","date_gmt":"2005-12-28T18:13:46","guid":{"rendered":"http:\/\/hunch.net\/?p=155"},"modified":"2005-12-28T12:14:04","modified_gmt":"2005-12-28T18:14:04","slug":"yet-more-nips-thoughts","status":"publish","type":"post","link":"https:\/\/hunch.net\/?p=155","title":{"rendered":"Yet more nips thoughts"},"content":{"rendered":"<p>I only managed to make it out to the NIPS workshops this year so<br \/>\nI&#8217;ll give my comments on what I saw there.  <\/p>\n<p>The Learing and Robotics workshops lives again. I hope it<br \/>\ncontinues and gets more high quality papers in the future. The<br \/>\nmost interesting talk for me was Larry Jackel&#8217;s on the LAGR<br \/>\nprogram (see John&#8217;s previous post on said program). I got some<br \/>\nideas as to what progress has been made. Larry really explained<br \/>\nthe types of benchmarks and the tradeoffs that had to be made to<br \/>\nmake the goals achievable but challenging. <\/p>\n<p>Hal Daume gave a very interesting talk about structured<br \/>\nprediction using RL techniques, something near and dear to my own<br \/>\nheart. He achieved rather impressive results using only a very<br \/>\ngreedy search.<\/p>\n<p>The non-parametric Bayes workshop was great. I enjoyed the entire<br \/>\nmorning session I spent there, and particularly (the usually<br \/>\ndesultory) discussion periods. One interesting topic was the<br \/>\nGibbs\/Variational inference divide. I won&#8217;t try to summarize<br \/>\nespecially as no conclusion was reached. It was interesting to<br \/>\nnote that samplers are competitive with the variational<br \/>\napproaches for many Dirichlet process problems. One open question<br \/>\nI left with was whether the fast variants of Gibbs sampling could<br \/>\nbe made multi-processor as the naive variants can.<\/p>\n<p>I also have a reading list of sorts from the main<br \/>\nconference. Most of the papers mentioned in previous posts on<br \/>\nNIPS are on that list as well as these: (in no particular order)<\/p>\n<p>The Information-Form Data Association Filter<br \/>\nSebastian Thrun, Brad Schumitsch, Gary Bradski, Kunle Olukotun<br \/>\n[ps.gz][pdf][bibtex]<\/p>\n<p>Divergences, surrogate loss functions and experimental design<br \/>\nXuanLong Nguyen, Martin Wainwright, Michael Jordan [ps.gz][pdf][bibtex]<\/p>\n<p>Generalization to Unseen Cases<br \/>\nTeemu Roos, Peter Gr\u00c3\u0192\u00c2\u00bcnwald, Petri Myllym\u00c3\u0192\u00c2\u00a4ki, Henry Tirri [ps.gz][pdf][bibtex]<\/p>\n<p>Gaussian Process Dynamical Models<br \/>\nDavid Fleet, Jack Wang, Aaron Hertzmann [ps.gz][pdf][bibtex]<\/p>\n<p>Convex Neural Networks<br \/>\nYoshua Bengio, Nicolas Le Roux, Pascal Vincent, Olivier Delalleau,<br \/>\nPatrice Marcotte [ps.gz][pdf][bibtex]<\/p>\n<p>Describing Visual Scenes using Transformed Dirichlet Processes<br \/>\nErik Sudderth, Antonio Torralba, William Freeman, Alan Willsky<br \/>\n[ps.gz][pdf][bibtex]<\/p>\n<p>Learning vehicular dynamics, with application to modeling helicopters<br \/>\nPieter Abbeel, Varun Ganapathi, Andrew Ng [ps.gz][pdf][bibtex]<\/p>\n<p>Tensor Subspace Analysis<br \/>\nXiaofei He, Deng Cai, Partha Niyogi [ps.gz][pdf][bibtex]<\/p>\n","protected":false},"excerpt":{"rendered":"<p>I only managed to make it out to the NIPS workshops this year so I&#8217;ll give my comments on what I saw there.  <\/p>\n","protected":false},"author":9,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-155","post","type-post","status-publish","format-standard","hentry","category-general"],"_links":{"self":[{"href":"https:\/\/hunch.net\/index.php?rest_route=\/wp\/v2\/posts\/155","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\/9"}],"replies":[{"embeddable":true,"href":"https:\/\/hunch.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=155"}],"version-history":[{"count":0,"href":"https:\/\/hunch.net\/index.php?rest_route=\/wp\/v2\/posts\/155\/revisions"}],"wp:attachment":[{"href":"https:\/\/hunch.net\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=155"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hunch.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=155"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hunch.net\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=155"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}