{"683592":{"#nid":"683592","#data":{"type":"event","title":"Machine Learning Seminar Series Spring 2026 | Deploying AI in an Open World: Principled and Practical OOD Detection","body":[{"value":"\u003Cdiv\u003E\u003Cp\u003E\u003Cstrong\u003EAbstract: \u003C\/strong\u003EModern machine learning systems achieve impressive performance, but are largely built under a closed-world assumption: that the data distribution does not change from the distribution of the training set. \u0026nbsp;Real environments are open, dynamic, and filled with unknown unknowns. In such settings, knowing when a model\u2019s output is reliable is critical.\u003C\/p\u003E\u003Cp\u003EThis talk focuses on out-of-distribution (OOD) detection, a key capability for safe and reliable AI. The first part presents a mathematical theory of OOD detection that places state-of-the-art methods, largely heuristically derived, within a unified variational information-theoretic framework [1]. \u0026nbsp;The theory provides plausible assumptions behind existing approaches and predicts new OOD detectors that are simple to implement and outperform state-of-the-art methods.\u003C\/p\u003E\u003Cp\u003EThe second part of the talk addresses an often overlooked problem in practical deployment of OOD detectors, that is, OOD detectors depend on parameters that must be tuned, and a \u201cgiven OOD\u201d dataset is required [2]. In practice, such given OOD data may be difficult to obtain. \u0026nbsp;We formalize this problem and introduce a new tuning strategy that uses only the model\u2019s training data and achieves similar or better performance compared to tuning on given OOD data, enabling robust and practical deployment.\u003C\/p\u003E\u003Cp\u003EThe ideas will be illustrated across applications including automatic target recognition, cyber-security, large language models, and radio-frequency (RF) fingerprinting.\u003C\/p\u003E\u003Cp\u003E[1] \u003Ca href=\u0022https:\/\/arxiv.org\/pdf\/2506.14194\u0022\u003Ehttps:\/\/arxiv.org\/pdf\/2506.14194\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E[2] \u003Ca href=\u0022https:\/\/arxiv.org\/pdf\/2602.05935\u0022\u003Ehttps:\/\/arxiv.org\/pdf\/2602.05935\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EBio: \u003C\/strong\u003EDr. Ganesh Sundaramoorthi is Senior Research Fellow\/Director of Research at RTX Technology Research Center, which is the research center for RTX (encompassing Raytheon, Collins Aerospace, and Pratt \u0026amp; Whitney) and also Adjunct Professor of ECE at Georgia Tech. \u0026nbsp;His research is in machine learning, computer vision, and artificial intelligence (AI), e.g., robustness, explainability, acceleration, and low size, weight \u0026amp; power.\u0026nbsp; Prior to his current position, he was on the faculty of KAUST, where he led a research group in computer vision.\u0026nbsp; His PhD was from Georgia Tech and he did postdoctoral work at UCLA in computer vision.\u0026nbsp;He has led a number of internal and external research programs in AI including IARPA, NGA, ARPA-E and AFRL. \u0026nbsp;He was area chair for leading AI conferences (IEEE\/CVF CVPR \u0026amp; ICCV). He has more than 60 publications in AI and nearly 50 patents and\/or applications.\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\u0022http:\/\/ganeshsun.com\/\u0022\u003Ehttp:\/\/ganeshsun.com\/\u003C\/a\u003E\u003C\/p\u003E\u003Ch3\u003E\u003Cem\u003EFor more information, or for CODA guest access, please contact \u003C\/em\u003E\u003Ca href=\u0022mailto:shatcher8@gatech.edu\u0022 title=\u0022mailto:shatcher8@gatech.edu\u0022\u003E\u003Cem\u003Eshatcher8@gatech.edu\u003C\/em\u003E\u003C\/a\u003E\u003Cem\u003E at least 2 business days prior to the event.\u003C\/em\u003E\u003C\/h3\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Ch5\u003E\u003Cstrong\u003EZOOM ACCESS\u0026nbsp;\u003C\/strong\u003E\u003C\/h5\u003E\u003Ch5\u003E\u003Ca href=\u0022https:\/\/gatech.zoom.us\/j\/92002341992?pwd=ZLAiI8WdAu8arEo23SEArIhGU2smxm.1\u0022 target=\u0022_blank\u0022 title=\u0022https:\/\/gatech.zoom.us\/j\/92002341992?pwd=ZLAiI8WdAu8arEo23SEArIhGU2smxm.1\u0022\u003Ehttps:\/\/gatech.zoom.us\/j\/92002341992?pwd=ZLAiI8WdAu8arEo23SEArIhGU2smxm.1\u003C\/a\u003E\u003C\/h5\u003E\u003Ch5\u003EMeeting ID: 920 0234 1992\u0026nbsp;\u003Cbr\u003EPasscode: 253459\u0026nbsp;\u003C\/h5\u003E\u003C\/div\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003E\u003Cstrong\u003EAll Seminars Held on Wednesdays 12pm - 1pm\u003C\/strong\u003E\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Featuring | Ganesh Sundaramoorthi - Senior Research Fellow\/Director of Research at RTX Technology Research Center"}],"uid":"27863","created_gmt":"2025-08-06 17:09:13","changed_gmt":"2026-02-11 18:54:45","author":"Christa Ernst","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2026-02-18T12:00:00-05:00","event_time_end":"2026-02-18T13:00:00-05:00","event_time_end_last":"2026-02-18T13:00:00-05:00","gmt_time_start":"2026-02-18 17:00:00","gmt_time_end":"2026-02-18 18:00:00","gmt_time_end_last":"2026-02-18 18:00:00","rrule":null,"timezone":"America\/New_York"},"location":"CODA Building 9th floor Atrium \u0026 Zoom","extras":[],"groups":[{"id":"322011","name":"College of Computing Events"},{"id":"1278","name":"College of Sciences"},{"id":"198081","name":"Georgia Electronic Design Center (GEDC)"},{"id":"545781","name":"Institute for Data Engineering and Science"},{"id":"142761","name":"IRIM"}],"categories":[],"keywords":[{"id":"9167","name":"machine learning"},{"id":"654","name":"College of Computing"},{"id":"187023","name":"go-data"},{"id":"1325","name":"aerospace"},{"id":"924","name":"national defense"},{"id":"187812","name":"artificial intelligence (AI)"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1795","name":"Seminar\/Lecture\/Colloquium"}],"invited_audience":[{"id":"78761","name":"Faculty\/Staff"},{"id":"177814","name":"Postdoc"},{"id":"78771","name":"Public"},{"id":"174045","name":"Graduate students"},{"id":"78751","name":"Undergraduate students"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003E\u003Ca href=\u0022mailto:shatcher8@gatech.edu\u0022 title=\u0022mailto:shatcher8@gatech.edu\u0022\u003E\u003Cem\u003Eshatcher8@gatech.edu\u003C\/em\u003E\u003C\/a\u003E\u003C\/p\u003E","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}}}