{"id":150,"date":"2005-12-14T23:47:38","date_gmt":"2005-12-15T05:47:38","guid":{"rendered":"http:\/\/hunch.net\/?p=150"},"modified":"2005-12-17T13:15:16","modified_gmt":"2005-12-17T19:15:16","slug":"more-nips-papers-ii","status":"publish","type":"post","link":"https:\/\/hunch.net\/?p=150","title":{"rendered":"More NIPS Papers II"},"content":{"rendered":"<p>I thought this was a very good NIPS with many excellent papers. The following are a few NIPS papers which I liked and I hope to study more carefully when I get the chance. The list is not exhaustive and in no particular order&#8230;<\/p>\n<ul>\n<li>Preconditioner Approximations for Probabilistic Graphical Models.<br \/>\nPradeeep Ravikumar and John Lafferty.<br \/>\nI thought the use of preconditioner methods from solving linear systems in the context of approximate inference was novel and interesting. The results look good and I&#8217;d like to understand the limitations.\n<\/li>\n<li>Rodeo: Sparse nonparametric regression in high dimensions.<br \/>\nJohn Lafferty and Larry Wasserman.<br \/>\nA very interesting approach to feature selection in nonparametric regression from a frequentist framework. The use of lengthscale variables in each dimension reminds me a lot of  &#8216;Automatic Relevance Determination&#8217; in Gaussian process regression &#8212; it would be interesting to compare Rodeo to ARD in GPs.\n<\/li>\n<li>Interpolating between types and tokens by estimating power law generators. <br \/> Goldwater, S., Griffiths, T. L., &#038; Johnson, M. <br \/>\nI had wondered how Chinese restaurant processes and Pitman-Yor processes related to Zipf&#8217;s plots and power laws for word frequencies. This paper seems to have the answers.\n<\/li>\n<li>A Bayesian spatial scan statistic. <br \/>\nDaniel B. Neill, Andrew W. Moore, and Gregory F. Cooper.<br \/>\nWhen I first learned about spatial scan statistics I wondered what a Bayesian counterpart would be. I liked the fact they their method was simple, more accurate, and much <em>faster<\/em> than the usual frequentist method.\n<\/li>\n<li>Q-Clustering. <br \/> M. Narasimhan, N. Jojic and J. Bilmes. <br \/>\nA very interesting application of sub-modular function optimization to clustering. This feels like a hot area.\n<\/li>\n<li> Worst-Case Bounds for Gaussian Process Models.<br \/>\nSham M. Kakade, Matthias W. Seeger, &#038; Dean P. Foster.<br \/> <br \/>\nIt&#8217;s useful for Gaussian process practitioners to know that their approaches don&#8217;t do silly things when viewed from a worst-case frequentist setting. This paper provides some relevant theoretical results.\n<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>Here are a few NIPS papers I liked and will try to follow up on&#8230;<\/p>\n","protected":false},"author":66,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[18],"tags":[],"class_list":["post-150","post","type-post","status-publish","format-standard","hentry","category-papers"],"_links":{"self":[{"href":"https:\/\/hunch.net\/index.php?rest_route=\/wp\/v2\/posts\/150","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\/66"}],"replies":[{"embeddable":true,"href":"https:\/\/hunch.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=150"}],"version-history":[{"count":0,"href":"https:\/\/hunch.net\/index.php?rest_route=\/wp\/v2\/posts\/150\/revisions"}],"wp:attachment":[{"href":"https:\/\/hunch.net\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=150"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hunch.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=150"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hunch.net\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=150"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}