{"id":12049,"date":"2025-12-24T09:14:44","date_gmt":"2025-12-24T00:14:44","guid":{"rendered":"https:\/\/www.ibs.re.kr\/bimag\/?post_type=tribe_events&p=12049"},"modified":"2025-12-24T09:15:28","modified_gmt":"2025-12-24T00:15:28","slug":"distribution-shift-in-machine-learning-robustness-invariance-and-a-causal-view-wooseok-ha","status":"publish","type":"tribe_events","link":"https:\/\/www.ibs.re.kr\/bimag\/event\/distribution-shift-in-machine-learning-robustness-invariance-and-a-causal-view-wooseok-ha\/","title":{"rendered":"Distribution shift in machine learning: robustness, invariance, and a causal view – Wooseok Ha"},"content":{"rendered":"
\n
\n
\n
\n
\n
\n
Classical machine learning models are typically trained under the assumption that the training (source) and test (target) data are drawn from the same distribution. However, real-world data are rarely clean or consistent, and distribution shifts between the source and target domains are ubiquitous. Despite its importance, addressing distribution shifts is highly difficult. The fundamental challenge is that the problem is mathematically ill-posed: shifts can occur in many different forms, and no single method can handle all of them. While\u00a0numerous algorithms have been proposed in recent years\u00a0to solve distribution shifts, most are empirical-driven and lack solid foundations. In this talk, I will provide a broad overview of approaches to address distribution shift based on invariance and distributional robustness, and explain how these methods are intrinsically connected to a causal perspective. In particular, I will show why\u00a0it is crucial to carefully formulate assumptions that relate the source and target domains for reliable generalization, and\u00a0how assumptions grounded in the causal system enable the analysis of algorithms under both unsupervised and semi-supervised settings.<\/span><\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
<\/div>\n<\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"

Classical machine learning models are typically trained under the assumption that the training (source) and test (target) data are drawn from the same distribution. However, real-world data are rarely clean … <\/p>\n

Continue reading “Distribution shift in machine learning: robustness, invariance, and a causal view – Wooseok Ha”<\/span><\/a><\/p>\n","protected":false},"author":11,"featured_media":0,"template":"","meta":{"_editorskit_title_hidden":false,"_editorskit_reading_time":0,"_editorskit_is_block_options_detached":false,"_editorskit_block_options_position":"{}","_uag_custom_page_level_css":"","_tribe_events_status":"","_tribe_events_status_reason":"","footnotes":""},"tags":[],"tribe_events_cat":[220],"class_list":["post-12049","tribe_events","type-tribe_events","status-publish","hentry","tribe_events_cat-biomedical-mathematics-seminar","cat_biomedical-mathematics-seminar"],"yoast_head":"\nDistribution shift in machine learning: robustness, invariance, and a causal view - Wooseok Ha - Biomedical Mathematics Group<\/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.ibs.re.kr\/bimag\/event\/distribution-shift-in-machine-learning-robustness-invariance-and-a-causal-view-wooseok-ha\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Distribution shift in machine learning: robustness, invariance, and a causal view - Wooseok Ha - Biomedical Mathematics Group\" \/>\n<meta property=\"og:description\" content=\"Classical machine learning models are typically trained under the assumption that the training (source) and test (target) data are drawn from the same distribution. However, real-world data are rarely clean … Continue reading "Distribution shift in machine learning: robustness, invariance, and a causal view – Wooseok Ha"\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.ibs.re.kr\/bimag\/event\/distribution-shift-in-machine-learning-robustness-invariance-and-a-causal-view-wooseok-ha\/\" \/>\n<meta property=\"og:site_name\" content=\"Biomedical Mathematics Group\" \/>\n<meta property=\"article:modified_time\" content=\"2025-12-24T00:15:28+00:00\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"1 minute\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/www.ibs.re.kr\\\/bimag\\\/event\\\/distribution-shift-in-machine-learning-robustness-invariance-and-a-causal-view-wooseok-ha\\\/\",\"url\":\"https:\\\/\\\/www.ibs.re.kr\\\/bimag\\\/event\\\/distribution-shift-in-machine-learning-robustness-invariance-and-a-causal-view-wooseok-ha\\\/\",\"name\":\"Distribution shift in machine learning: robustness, invariance, and a causal view - Wooseok Ha - Biomedical Mathematics Group\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.ibs.re.kr\\\/bimag\\\/#website\"},\"datePublished\":\"2025-12-24T00:14:44+00:00\",\"dateModified\":\"2025-12-24T00:15:28+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/www.ibs.re.kr\\\/bimag\\\/event\\\/distribution-shift-in-machine-learning-robustness-invariance-and-a-causal-view-wooseok-ha\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/www.ibs.re.kr\\\/bimag\\\/event\\\/distribution-shift-in-machine-learning-robustness-invariance-and-a-causal-view-wooseok-ha\\\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/www.ibs.re.kr\\\/bimag\\\/event\\\/distribution-shift-in-machine-learning-robustness-invariance-and-a-causal-view-wooseok-ha\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/www.ibs.re.kr\\\/bimag\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Events\",\"item\":\"https:\\\/\\\/www.ibs.re.kr\\\/bimag\\\/events\\\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"Distribution shift in machine learning: robustness, invariance, and a causal view – Wooseok Ha\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/www.ibs.re.kr\\\/bimag\\\/#website\",\"url\":\"https:\\\/\\\/www.ibs.re.kr\\\/bimag\\\/\",\"name\":\"Biomedical Mathematics Group\",\"description\":\"\uae30\ucd08\uacfc\ud559\uc5f0\uad6c\uc6d0 \uc758\uc0dd\uba85\uc218\ud559\uadf8\ub8f9\",\"publisher\":{\"@id\":\"https:\\\/\\\/www.ibs.re.kr\\\/bimag\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/www.ibs.re.kr\\\/bimag\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/www.ibs.re.kr\\\/bimag\\\/#organization\",\"name\":\"IBS Biomedical Mathematics Group\",\"url\":\"https:\\\/\\\/www.ibs.re.kr\\\/bimag\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/www.ibs.re.kr\\\/bimag\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/www.ibs.re.kr\\\/bimag\\\/cms\\\/wp-content\\\/uploads\\\/2021\\\/02\\\/ibs-circle-1.png\",\"contentUrl\":\"https:\\\/\\\/www.ibs.re.kr\\\/bimag\\\/cms\\\/wp-content\\\/uploads\\\/2021\\\/02\\\/ibs-circle-1.png\",\"width\":250,\"height\":250,\"caption\":\"IBS Biomedical Mathematics Group\"},\"image\":{\"@id\":\"https:\\\/\\\/www.ibs.re.kr\\\/bimag\\\/#\\\/schema\\\/logo\\\/image\\\/\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Distribution shift in machine learning: robustness, invariance, and a causal view - Wooseok Ha - Biomedical Mathematics Group","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.ibs.re.kr\/bimag\/event\/distribution-shift-in-machine-learning-robustness-invariance-and-a-causal-view-wooseok-ha\/","og_locale":"en_US","og_type":"article","og_title":"Distribution shift in machine learning: robustness, invariance, and a causal view - Wooseok Ha - Biomedical Mathematics Group","og_description":"Classical machine learning models are typically trained under the assumption that the training (source) and test (target) data are drawn from the same distribution. However, real-world data are rarely clean … Continue reading \"Distribution shift in machine learning: robustness, invariance, and a causal view – Wooseok Ha\"","og_url":"https:\/\/www.ibs.re.kr\/bimag\/event\/distribution-shift-in-machine-learning-robustness-invariance-and-a-causal-view-wooseok-ha\/","og_site_name":"Biomedical Mathematics Group","article_modified_time":"2025-12-24T00:15:28+00:00","twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"1 minute"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.ibs.re.kr\/bimag\/event\/distribution-shift-in-machine-learning-robustness-invariance-and-a-causal-view-wooseok-ha\/","url":"https:\/\/www.ibs.re.kr\/bimag\/event\/distribution-shift-in-machine-learning-robustness-invariance-and-a-causal-view-wooseok-ha\/","name":"Distribution shift in machine learning: robustness, invariance, and a causal view - Wooseok Ha - Biomedical Mathematics Group","isPartOf":{"@id":"https:\/\/www.ibs.re.kr\/bimag\/#website"},"datePublished":"2025-12-24T00:14:44+00:00","dateModified":"2025-12-24T00:15:28+00:00","breadcrumb":{"@id":"https:\/\/www.ibs.re.kr\/bimag\/event\/distribution-shift-in-machine-learning-robustness-invariance-and-a-causal-view-wooseok-ha\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.ibs.re.kr\/bimag\/event\/distribution-shift-in-machine-learning-robustness-invariance-and-a-causal-view-wooseok-ha\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.ibs.re.kr\/bimag\/event\/distribution-shift-in-machine-learning-robustness-invariance-and-a-causal-view-wooseok-ha\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.ibs.re.kr\/bimag\/"},{"@type":"ListItem","position":2,"name":"Events","item":"https:\/\/www.ibs.re.kr\/bimag\/events\/"},{"@type":"ListItem","position":3,"name":"Distribution shift in machine learning: robustness, invariance, and a causal view – Wooseok Ha"}]},{"@type":"WebSite","@id":"https:\/\/www.ibs.re.kr\/bimag\/#website","url":"https:\/\/www.ibs.re.kr\/bimag\/","name":"Biomedical Mathematics Group","description":"\uae30\ucd08\uacfc\ud559\uc5f0\uad6c\uc6d0 \uc758\uc0dd\uba85\uc218\ud559\uadf8\ub8f9","publisher":{"@id":"https:\/\/www.ibs.re.kr\/bimag\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.ibs.re.kr\/bimag\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.ibs.re.kr\/bimag\/#organization","name":"IBS Biomedical Mathematics Group","url":"https:\/\/www.ibs.re.kr\/bimag\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.ibs.re.kr\/bimag\/#\/schema\/logo\/image\/","url":"https:\/\/www.ibs.re.kr\/bimag\/cms\/wp-content\/uploads\/2021\/02\/ibs-circle-1.png","contentUrl":"https:\/\/www.ibs.re.kr\/bimag\/cms\/wp-content\/uploads\/2021\/02\/ibs-circle-1.png","width":250,"height":250,"caption":"IBS Biomedical Mathematics Group"},"image":{"@id":"https:\/\/www.ibs.re.kr\/bimag\/#\/schema\/logo\/image\/"}}]}},"uagb_featured_image_src":{"full":false,"thumbnail":false,"medium":false,"medium_large":false,"large":false,"1536x1536":false,"2048x2048":false,"dimag-thumbnail":false,"twentyseventeen-featured-image":false,"twentyseventeen-thumbnail-avatar":false},"uagb_author_info":{"display_name":"Gyuyoung","author_link":"https:\/\/www.ibs.re.kr\/bimag\/author\/gyuyoung\/"},"uagb_comment_info":0,"uagb_excerpt":"Classical machine learning models are typically trained under the assumption that the training (source) and test (target) data are drawn from the same distribution. However, real-world data are rarely clean … Continue reading \"Distribution shift in machine learning: robustness, invariance, and a causal view – Wooseok Ha\"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/www.ibs.re.kr\/bimag\/wp-json\/wp\/v2\/tribe_events\/12049","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.ibs.re.kr\/bimag\/wp-json\/wp\/v2\/tribe_events"}],"about":[{"href":"https:\/\/www.ibs.re.kr\/bimag\/wp-json\/wp\/v2\/types\/tribe_events"}],"author":[{"embeddable":true,"href":"https:\/\/www.ibs.re.kr\/bimag\/wp-json\/wp\/v2\/users\/11"}],"version-history":[{"count":1,"href":"https:\/\/www.ibs.re.kr\/bimag\/wp-json\/wp\/v2\/tribe_events\/12049\/revisions"}],"predecessor-version":[{"id":12050,"href":"https:\/\/www.ibs.re.kr\/bimag\/wp-json\/wp\/v2\/tribe_events\/12049\/revisions\/12050"}],"wp:attachment":[{"href":"https:\/\/www.ibs.re.kr\/bimag\/wp-json\/wp\/v2\/media?parent=12049"}],"wp:term":[{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.ibs.re.kr\/bimag\/wp-json\/wp\/v2\/tags?post=12049"},{"taxonomy":"tribe_events_cat","embeddable":true,"href":"https:\/\/www.ibs.re.kr\/bimag\/wp-json\/wp\/v2\/tribe_events_cat?post=12049"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}