{"id":12661,"date":"2026-06-29T17:11:20","date_gmt":"2026-06-29T08:11:20","guid":{"rendered":"https:\/\/www.ibs.re.kr\/bimag\/?post_type=tribe_events&p=12661"},"modified":"2026-07-30T11:07:23","modified_gmt":"2026-07-30T02:07:23","slug":"oscillatory-network-efficiency-predicts-mood-and-fatigue-during-sleep-deprivation-seunghun-lee","status":"publish","type":"tribe_events","link":"https:\/\/www.ibs.re.kr\/bimag\/event\/oscillatory-network-efficiency-predicts-mood-and-fatigue-during-sleep-deprivation-seunghun-lee\/","title":{"rendered":"Fast training of accurate physics-informed neural networks without gradient descent – Seunghun Lee"},"content":{"rendered":"

In this talk, we discuss the paper \u201cFast training of accurate physics-informed neural networks without gradient descent\u201d by Chinmay Datar et al., ICLR<\/em>, 2026.<\/p>\n

Abstract:<\/p>\n

Solving time-dependent Partial Differential Equations (PDEs) is one of the most critical problems in computational science. While Physics-Informed Neural Networks (PINNs) offer a promising framework for approximating PDE solutions, their accuracy and training speed are limited by two core barriers: gradient-descent-based iterative optimization over complex loss landscapes and non-causal treatment of time as an extra spatial dimension. We present Frozen-PINN, a novel PINN based on the principle of space-time separation that leverages random features instead of training with gradient descent, and incorporates temporal causality by construction. On nine PDE benchmarks, including challenges like extreme advection speeds, shocks, and high-dimensionality, Frozen-PINNs achieve superior training efficiency and accuracy over state-of-the-art PINNs, often by several orders of magnitude. Our work addresses longstanding training and accuracy bottlenecks of PINNs, delivering quickly trainable, highly accurate, and inherently causal PDE solvers, a combination that prior methods could not realize. Our approach challenges the reliance of PINNs on stochastic gradient-descent-based methods and specialized hardware, leading to a paradigm shift in PINN training and providing a challenging benchmark for the community.<\/p>\n","protected":false},"excerpt":{"rendered":"

In this talk, we discuss the paper \u201cFast training of accurate physics-informed neural networks without gradient descent\u201d by Chinmay Datar et al., ICLR, 2026. Abstract: Solving time-dependent Partial Differential Equations … <\/p>\n

Continue reading “Fast training of accurate physics-informed neural networks without gradient descent – Seunghun Lee”<\/span><\/a><\/p>\n","protected":false},"author":13,"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":[219],"class_list":["post-12661","tribe_events","type-tribe_events","status-publish","hentry","tribe_events_cat-journal-club","cat_journal-club"],"yoast_head":"\nFast training of accurate physics-informed neural networks without gradient descent - Seunghun Lee - Biomedical Mathematics Group<\/title>\n<meta name=\"description\" content=\"Fluctuations in performance and mood across the day have been traced to circadian and homeostatic modulation of motor and affective systems, although their combined influence on network topology is rarely considered. We applied a data-driven curve-fitting algorithm to capture both circadian and infradian rhythms (\u2009\u2265\u200924\u2009hours) in frontolimbic and sensorimotor regions using\u00a0functional magnetic resonance imaging (fMRI) measures of connectivity. Across the course of sleep deprivation, functional network structure was not static but changed in tandem with objective and subjective behavioral measures. Oscillatory patterns in network efficiency suggest that circadian rhythmicity extends to higher-order network topology. Sleep deprivation affects functional networks in a region-specific manner, highlighting local vulnerability. Distinct cortical regions exhibited unique circadian phases of network reorganization, revealing that connectivity rhythms are spatially as well as temporally differentiated across the brain. Time-dependent alterations in connectome topology offer a systems-level framework for understanding how internal timekeeping and sleep pressure modulate non-linear trends in psychomotor vigilance, mood, and fatigue across extended wakefulness.\" \/>\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\/oscillatory-network-efficiency-predicts-mood-and-fatigue-during-sleep-deprivation-seunghun-lee\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Fast training of accurate physics-informed neural networks without gradient descent - Seunghun Lee - Biomedical Mathematics Group\" \/>\n<meta property=\"og:description\" content=\"Fluctuations in performance and mood across the day have been traced to circadian and homeostatic modulation of motor and affective systems, although their combined influence on network topology is rarely considered. We applied a data-driven curve-fitting algorithm to capture both circadian and infradian rhythms (\u2009\u2265\u200924\u2009hours) in frontolimbic and sensorimotor regions using\u00a0functional magnetic resonance imaging (fMRI) measures of connectivity. Across the course of sleep deprivation, functional network structure was not static but changed in tandem with objective and subjective behavioral measures. Oscillatory patterns in network efficiency suggest that circadian rhythmicity extends to higher-order network topology. Sleep deprivation affects functional networks in a region-specific manner, highlighting local vulnerability. Distinct cortical regions exhibited unique circadian phases of network reorganization, revealing that connectivity rhythms are spatially as well as temporally differentiated across the brain. Time-dependent alterations in connectome topology offer a systems-level framework for understanding how internal timekeeping and sleep pressure modulate non-linear trends in psychomotor vigilance, mood, and fatigue across extended wakefulness.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.ibs.re.kr\/bimag\/event\/oscillatory-network-efficiency-predicts-mood-and-fatigue-during-sleep-deprivation-seunghun-lee\/\" \/>\n<meta property=\"og:site_name\" content=\"Biomedical Mathematics Group\" \/>\n<meta property=\"article:modified_time\" content=\"2026-07-30T02:07:23+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\\\/oscillatory-network-efficiency-predicts-mood-and-fatigue-during-sleep-deprivation-seunghun-lee\\\/\",\"url\":\"https:\\\/\\\/www.ibs.re.kr\\\/bimag\\\/event\\\/oscillatory-network-efficiency-predicts-mood-and-fatigue-during-sleep-deprivation-seunghun-lee\\\/\",\"name\":\"Fast training of accurate physics-informed neural networks without gradient descent - Seunghun Lee - Biomedical Mathematics Group\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.ibs.re.kr\\\/bimag\\\/#website\"},\"datePublished\":\"2026-06-29T08:11:20+00:00\",\"dateModified\":\"2026-07-30T02:07:23+00:00\",\"description\":\"Fluctuations in performance and mood across the day have been traced to circadian and homeostatic modulation of motor and affective systems, although their combined influence on network topology is rarely considered. We applied a data-driven curve-fitting algorithm to capture both circadian and infradian rhythms (\u2009\u2265\u200924\u2009hours) in frontolimbic and sensorimotor regions using\u00a0functional magnetic resonance imaging (fMRI) measures of connectivity. Across the course of sleep deprivation, functional network structure was not static but changed in tandem with objective and subjective behavioral measures. Oscillatory patterns in network efficiency suggest that circadian rhythmicity extends to higher-order network topology. Sleep deprivation affects functional networks in a region-specific manner, highlighting local vulnerability. Distinct cortical regions exhibited unique circadian phases of network reorganization, revealing that connectivity rhythms are spatially as well as temporally differentiated across the brain. Time-dependent alterations in connectome topology offer a systems-level framework for understanding how internal timekeeping and sleep pressure modulate non-linear trends in psychomotor vigilance, mood, and fatigue across extended wakefulness.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/www.ibs.re.kr\\\/bimag\\\/event\\\/oscillatory-network-efficiency-predicts-mood-and-fatigue-during-sleep-deprivation-seunghun-lee\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/www.ibs.re.kr\\\/bimag\\\/event\\\/oscillatory-network-efficiency-predicts-mood-and-fatigue-during-sleep-deprivation-seunghun-lee\\\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/www.ibs.re.kr\\\/bimag\\\/event\\\/oscillatory-network-efficiency-predicts-mood-and-fatigue-during-sleep-deprivation-seunghun-lee\\\/#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\":\"Fast training of accurate physics-informed neural networks without gradient descent – Seunghun Lee\"}]},{\"@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":"Fast training of accurate physics-informed neural networks without gradient descent - Seunghun Lee - Biomedical Mathematics Group","description":"Fluctuations in performance and mood across the day have been traced to circadian and homeostatic modulation of motor and affective systems, although their combined influence on network topology is rarely considered. We applied a data-driven curve-fitting algorithm to capture both circadian and infradian rhythms (\u2009\u2265\u200924\u2009hours) in frontolimbic and sensorimotor regions using\u00a0functional magnetic resonance imaging (fMRI) measures of connectivity. Across the course of sleep deprivation, functional network structure was not static but changed in tandem with objective and subjective behavioral measures. Oscillatory patterns in network efficiency suggest that circadian rhythmicity extends to higher-order network topology. Sleep deprivation affects functional networks in a region-specific manner, highlighting local vulnerability. Distinct cortical regions exhibited unique circadian phases of network reorganization, revealing that connectivity rhythms are spatially as well as temporally differentiated across the brain. Time-dependent alterations in connectome topology offer a systems-level framework for understanding how internal timekeeping and sleep pressure modulate non-linear trends in psychomotor vigilance, mood, and fatigue across extended wakefulness.","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\/oscillatory-network-efficiency-predicts-mood-and-fatigue-during-sleep-deprivation-seunghun-lee\/","og_locale":"en_US","og_type":"article","og_title":"Fast training of accurate physics-informed neural networks without gradient descent - Seunghun Lee - Biomedical Mathematics Group","og_description":"Fluctuations in performance and mood across the day have been traced to circadian and homeostatic modulation of motor and affective systems, although their combined influence on network topology is rarely considered. We applied a data-driven curve-fitting algorithm to capture both circadian and infradian rhythms (\u2009\u2265\u200924\u2009hours) in frontolimbic and sensorimotor regions using\u00a0functional magnetic resonance imaging (fMRI) measures of connectivity. Across the course of sleep deprivation, functional network structure was not static but changed in tandem with objective and subjective behavioral measures. Oscillatory patterns in network efficiency suggest that circadian rhythmicity extends to higher-order network topology. Sleep deprivation affects functional networks in a region-specific manner, highlighting local vulnerability. Distinct cortical regions exhibited unique circadian phases of network reorganization, revealing that connectivity rhythms are spatially as well as temporally differentiated across the brain. Time-dependent alterations in connectome topology offer a systems-level framework for understanding how internal timekeeping and sleep pressure modulate non-linear trends in psychomotor vigilance, mood, and fatigue across extended wakefulness.","og_url":"https:\/\/www.ibs.re.kr\/bimag\/event\/oscillatory-network-efficiency-predicts-mood-and-fatigue-during-sleep-deprivation-seunghun-lee\/","og_site_name":"Biomedical Mathematics Group","article_modified_time":"2026-07-30T02:07:23+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\/oscillatory-network-efficiency-predicts-mood-and-fatigue-during-sleep-deprivation-seunghun-lee\/","url":"https:\/\/www.ibs.re.kr\/bimag\/event\/oscillatory-network-efficiency-predicts-mood-and-fatigue-during-sleep-deprivation-seunghun-lee\/","name":"Fast training of accurate physics-informed neural networks without gradient descent - Seunghun Lee - Biomedical Mathematics Group","isPartOf":{"@id":"https:\/\/www.ibs.re.kr\/bimag\/#website"},"datePublished":"2026-06-29T08:11:20+00:00","dateModified":"2026-07-30T02:07:23+00:00","description":"Fluctuations in performance and mood across the day have been traced to circadian and homeostatic modulation of motor and affective systems, although their combined influence on network topology is rarely considered. We applied a data-driven curve-fitting algorithm to capture both circadian and infradian rhythms (\u2009\u2265\u200924\u2009hours) in frontolimbic and sensorimotor regions using\u00a0functional magnetic resonance imaging (fMRI) measures of connectivity. Across the course of sleep deprivation, functional network structure was not static but changed in tandem with objective and subjective behavioral measures. Oscillatory patterns in network efficiency suggest that circadian rhythmicity extends to higher-order network topology. Sleep deprivation affects functional networks in a region-specific manner, highlighting local vulnerability. Distinct cortical regions exhibited unique circadian phases of network reorganization, revealing that connectivity rhythms are spatially as well as temporally differentiated across the brain. Time-dependent alterations in connectome topology offer a systems-level framework for understanding how internal timekeeping and sleep pressure modulate non-linear trends in psychomotor vigilance, mood, and fatigue across extended wakefulness.","breadcrumb":{"@id":"https:\/\/www.ibs.re.kr\/bimag\/event\/oscillatory-network-efficiency-predicts-mood-and-fatigue-during-sleep-deprivation-seunghun-lee\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.ibs.re.kr\/bimag\/event\/oscillatory-network-efficiency-predicts-mood-and-fatigue-during-sleep-deprivation-seunghun-lee\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.ibs.re.kr\/bimag\/event\/oscillatory-network-efficiency-predicts-mood-and-fatigue-during-sleep-deprivation-seunghun-lee\/#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":"Fast training of accurate physics-informed neural networks without gradient descent – Seunghun Lee"}]},{"@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":"Hyeong Jun Jang","author_link":"https:\/\/www.ibs.re.kr\/bimag\/author\/hyeong-jun-jang\/"},"uagb_comment_info":0,"uagb_excerpt":"In this talk, we discuss the paper \u201cFast training of accurate physics-informed neural networks without gradient descent\u201d by Chinmay Datar et al., ICLR, 2026. Abstract: Solving time-dependent Partial Differential Equations … Continue reading \"Fast training of accurate physics-informed neural networks without gradient descent – Seunghun Lee\"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/www.ibs.re.kr\/bimag\/wp-json\/wp\/v2\/tribe_events\/12661","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\/13"}],"version-history":[{"count":3,"href":"https:\/\/www.ibs.re.kr\/bimag\/wp-json\/wp\/v2\/tribe_events\/12661\/revisions"}],"predecessor-version":[{"id":12739,"href":"https:\/\/www.ibs.re.kr\/bimag\/wp-json\/wp\/v2\/tribe_events\/12661\/revisions\/12739"}],"wp:attachment":[{"href":"https:\/\/www.ibs.re.kr\/bimag\/wp-json\/wp\/v2\/media?parent=12661"}],"wp:term":[{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.ibs.re.kr\/bimag\/wp-json\/wp\/v2\/tags?post=12661"},{"taxonomy":"tribe_events_cat","embeddable":true,"href":"https:\/\/www.ibs.re.kr\/bimag\/wp-json\/wp\/v2\/tribe_events_cat?post=12661"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}