{"id":3785,"date":"2021-02-24T13:33:11","date_gmt":"2021-02-24T12:33:11","guid":{"rendered":"https:\/\/www.ceessnoek.info\/?p=3785"},"modified":"2021-02-24T13:49:19","modified_gmt":"2021-02-24T12:49:19","slug":"iclr2021-set-prediction","status":"publish","type":"post","link":"https:\/\/www.ceessnoek.info\/index.php\/iclr2021-set-prediction\/","title":{"rendered":"ICLR2021: Set Prediction"},"content":{"rendered":"\n<p>The cam-ready of the ICLR 2021 paper &#8220;<em>Set Prediction without Imposing Structure as Conditional Density Estimation<\/em>&#8221; by David Zhang, Gertjan Burghouts and Cees Snoek is <a href=\"https:\/\/arxiv.org\/abs\/2010.04109\">now available<\/a>. Set prediction is about learning to predict a collection of unordered variables with unknown interrelations. Training such models with set losses imposes the structure of a metric space over sets. We focus on stochastic and underdefined cases, where an incorrectly chosen loss function leads to implausible predictions. Example tasks include conditional point-cloud reconstruction and predicting future states of molecules. In this paper, we propose an alternative to training via set losses by viewing learning as conditional density estimation. Our learning framework fits deep energy-based models and approximates the intractable likelihood with gradient-guided sampling. Furthermore, we propose a stochastically augmented prediction algorithm that enables multiple predictions, reflecting the possible variations in the target set. We empirically demonstrate on a variety of datasets the capability to learn multi-modal densities and produce different plausible predictions. Our approach is competitive with previous set prediction models on standard benchmarks. More importantly, it extends the family of addressable tasks beyond those that have unambiguous predictions.<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><a href=\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/01\/zhang-set.png\"><img loading=\"lazy\" decoding=\"async\" width=\"848\" height=\"424\" src=\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/01\/zhang-set.png\" alt=\"\" class=\"wp-image-3778\" srcset=\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/01\/zhang-set.png 848w, https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/01\/zhang-set-300x150.png 300w, https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/01\/zhang-set-768x384.png 768w\" sizes=\"auto, (max-width: 848px) 100vw, 848px\" \/><\/a><\/figure>\n","protected":false},"excerpt":{"rendered":"<p>The cam-ready of the ICLR 2021 paper &#8220;Set Prediction without Imposing Structure as Conditional Density Estimation&#8221; by David Zhang, Gertjan Burghouts and Cees Snoek is now available. Set prediction is about learning to predict a collection of unordered variables with unknown interrelations. Training such models with set losses imposes the structure of a metric space [&hellip;]<\/p>\n","protected":false},"author":3,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[4],"tags":[],"class_list":["post-3785","post","type-post","status-publish","format-standard","hentry","category-science"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v25.3 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>ICLR2021: Set Prediction - Cees Snoek<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.ceessnoek.info\/index.php\/iclr2021-set-prediction\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"ICLR2021: Set Prediction - Cees Snoek\" \/>\n<meta property=\"og:description\" content=\"The cam-ready of the ICLR 2021 paper &#8220;Set Prediction without Imposing Structure as Conditional Density Estimation&#8221; by David Zhang, Gertjan Burghouts and Cees Snoek is now available. Set prediction is about learning to predict a collection of unordered variables with unknown interrelations. Training such models with set losses imposes the structure of a metric space [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.ceessnoek.info\/index.php\/iclr2021-set-prediction\/\" \/>\n<meta property=\"og:site_name\" content=\"Cees Snoek\" \/>\n<meta property=\"article:published_time\" content=\"2021-02-24T12:33:11+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2021-02-24T12:49:19+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/01\/zhang-set.png\" \/>\n<meta name=\"author\" content=\"Cees\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Cees\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.ceessnoek.info\/index.php\/iclr2021-set-prediction\/\",\"url\":\"https:\/\/www.ceessnoek.info\/index.php\/iclr2021-set-prediction\/\",\"name\":\"ICLR2021: Set Prediction - Cees Snoek\",\"isPartOf\":{\"@id\":\"https:\/\/www.ceessnoek.info\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.ceessnoek.info\/index.php\/iclr2021-set-prediction\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.ceessnoek.info\/index.php\/iclr2021-set-prediction\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/01\/zhang-set.png\",\"datePublished\":\"2021-02-24T12:33:11+00:00\",\"dateModified\":\"2021-02-24T12:49:19+00:00\",\"author\":{\"@id\":\"https:\/\/www.ceessnoek.info\/#\/schema\/person\/4bca975b7c432aeb5dced40bdbc204c1\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.ceessnoek.info\/index.php\/iclr2021-set-prediction\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.ceessnoek.info\/index.php\/iclr2021-set-prediction\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.ceessnoek.info\/index.php\/iclr2021-set-prediction\/#primaryimage\",\"url\":\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/01\/zhang-set.png\",\"contentUrl\":\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/01\/zhang-set.png\",\"width\":848,\"height\":424},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.ceessnoek.info\/index.php\/iclr2021-set-prediction\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.ceessnoek.info\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"ICLR2021: Set Prediction\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.ceessnoek.info\/#website\",\"url\":\"https:\/\/www.ceessnoek.info\/\",\"name\":\"Cees Snoek\",\"description\":\"research on video and image ai\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.ceessnoek.info\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.ceessnoek.info\/#\/schema\/person\/4bca975b7c432aeb5dced40bdbc204c1\",\"name\":\"Cees\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.ceessnoek.info\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/756ccb993852c1e8e3af39a228d11a7305b2a937750f26dc5799d5df019b0f51?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/756ccb993852c1e8e3af39a228d11a7305b2a937750f26dc5799d5df019b0f51?s=96&d=mm&r=g\",\"caption\":\"Cees\"},\"sameAs\":[\"http:\/\/www.CeesSnoek.info\"],\"url\":\"https:\/\/www.ceessnoek.info\/index.php\/author\/admin\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"ICLR2021: Set Prediction - Cees Snoek","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.ceessnoek.info\/index.php\/iclr2021-set-prediction\/","og_locale":"en_US","og_type":"article","og_title":"ICLR2021: Set Prediction - Cees Snoek","og_description":"The cam-ready of the ICLR 2021 paper &#8220;Set Prediction without Imposing Structure as Conditional Density Estimation&#8221; by David Zhang, Gertjan Burghouts and Cees Snoek is now available. Set prediction is about learning to predict a collection of unordered variables with unknown interrelations. Training such models with set losses imposes the structure of a metric space [&hellip;]","og_url":"https:\/\/www.ceessnoek.info\/index.php\/iclr2021-set-prediction\/","og_site_name":"Cees Snoek","article_published_time":"2021-02-24T12:33:11+00:00","article_modified_time":"2021-02-24T12:49:19+00:00","og_image":[{"url":"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/01\/zhang-set.png","type":"","width":"","height":""}],"author":"Cees","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Cees","Est. reading time":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.ceessnoek.info\/index.php\/iclr2021-set-prediction\/","url":"https:\/\/www.ceessnoek.info\/index.php\/iclr2021-set-prediction\/","name":"ICLR2021: Set Prediction - Cees Snoek","isPartOf":{"@id":"https:\/\/www.ceessnoek.info\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.ceessnoek.info\/index.php\/iclr2021-set-prediction\/#primaryimage"},"image":{"@id":"https:\/\/www.ceessnoek.info\/index.php\/iclr2021-set-prediction\/#primaryimage"},"thumbnailUrl":"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/01\/zhang-set.png","datePublished":"2021-02-24T12:33:11+00:00","dateModified":"2021-02-24T12:49:19+00:00","author":{"@id":"https:\/\/www.ceessnoek.info\/#\/schema\/person\/4bca975b7c432aeb5dced40bdbc204c1"},"breadcrumb":{"@id":"https:\/\/www.ceessnoek.info\/index.php\/iclr2021-set-prediction\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.ceessnoek.info\/index.php\/iclr2021-set-prediction\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.ceessnoek.info\/index.php\/iclr2021-set-prediction\/#primaryimage","url":"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/01\/zhang-set.png","contentUrl":"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/01\/zhang-set.png","width":848,"height":424},{"@type":"BreadcrumbList","@id":"https:\/\/www.ceessnoek.info\/index.php\/iclr2021-set-prediction\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.ceessnoek.info\/"},{"@type":"ListItem","position":2,"name":"ICLR2021: Set Prediction"}]},{"@type":"WebSite","@id":"https:\/\/www.ceessnoek.info\/#website","url":"https:\/\/www.ceessnoek.info\/","name":"Cees Snoek","description":"research on video and image ai","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.ceessnoek.info\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/www.ceessnoek.info\/#\/schema\/person\/4bca975b7c432aeb5dced40bdbc204c1","name":"Cees","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.ceessnoek.info\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/756ccb993852c1e8e3af39a228d11a7305b2a937750f26dc5799d5df019b0f51?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/756ccb993852c1e8e3af39a228d11a7305b2a937750f26dc5799d5df019b0f51?s=96&d=mm&r=g","caption":"Cees"},"sameAs":["http:\/\/www.CeesSnoek.info"],"url":"https:\/\/www.ceessnoek.info\/index.php\/author\/admin\/"}]}},"_links":{"self":[{"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/posts\/3785","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/comments?post=3785"}],"version-history":[{"count":3,"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/posts\/3785\/revisions"}],"predecessor-version":[{"id":3789,"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/posts\/3785\/revisions\/3789"}],"wp:attachment":[{"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/media?parent=3785"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/categories?post=3785"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/tags?post=3785"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}