{"id":61,"date":"2005-04-14T16:41:01","date_gmt":"2005-04-14T22:41:01","guid":{"rendered":"\/?p=61"},"modified":"2005-04-14T16:41:05","modified_gmt":"2005-04-14T22:41:05","slug":"families-of-learning-theory-statements","status":"publish","type":"post","link":"https:\/\/hunch.net\/?p=61","title":{"rendered":"Families of Learning Theory Statements"},"content":{"rendered":"<p><img decoding=\"async\" src=\"https:\/\/hunch.net\/~jl\/projects\/past_future.jpg\"><\/p>\n<p>The diagram above shows a very broad viewpoint of learning theory. <\/p>\n<table border=1>\n<tr>\n<td>arrow<\/td>\n<td>Typical statement<\/td>\n<td>Examples<\/td>\n<\/tr>\n<tr>\n<td>Past->Past<\/td>\n<td> Some prediction algorithm <em>A<\/em> does almost as well as any of a set of algorithms.<\/td>\n<td>Weighted Majority<\/td>\n<\/tr>\n<tr>\n<td>Past->Future<\/td>\n<td>Assuming independent samples, past performance predicts future performance.<\/td>\n<td>PAC analysis, ERM analysis<\/td>\n<\/tr>\n<tr>\n<td>Future->Future<\/td>\n<td>Future prediction performance on subproblems implies future prediction performance using algorithm <em>A<\/em>.<\/td>\n<td>ECOC, Probing<\/td>\n<\/tr>\n<\/table>\n<p>A basic question is: Are there other varieties of statements of this type?  <a href=\"http:\/\/www-2.cs.cmu.edu\/~avrim\/\">Avrim<\/a> noted that there are also &#8220;arrows between arrows&#8221;: generic methods for transforming between Past->Past statements and Past->Future statements.  Are there others? <\/p>\n","protected":false},"excerpt":{"rendered":"<p>The diagram above shows a very broad viewpoint of learning theory. arrow Typical statement Examples Past->Past Some prediction algorithm A does almost as well as any of a set of algorithms. Weighted Majority Past->Future Assuming independent samples, past performance predicts future performance. PAC analysis, ERM analysis Future->Future Future prediction performance on subproblems implies future prediction &hellip; <\/p>\n<p class=\"link-more\"><a href=\"https:\/\/hunch.net\/?p=61\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;Families of Learning Theory Statements&#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":[3],"tags":[],"class_list":["post-61","post","type-post","status-publish","format-standard","hentry","category-organization"],"_links":{"self":[{"href":"https:\/\/hunch.net\/index.php?rest_route=\/wp\/v2\/posts\/61","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=61"}],"version-history":[{"count":0,"href":"https:\/\/hunch.net\/index.php?rest_route=\/wp\/v2\/posts\/61\/revisions"}],"wp:attachment":[{"href":"https:\/\/hunch.net\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=61"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hunch.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=61"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hunch.net\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=61"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}