BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
CALSCALE:GREGORIAN
PRODID:-//WordPress - MECv6.5.6//EN
X-ORIGINAL-URL:https://cmc.deusto.eus/
X-WR-CALNAME:cmc.deusto.eus
X-WR-CALDESC:DeustoCCM - Chair of Computational Mathematics at University of Deusto
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-PUBLISHED-TTL:PT1H
X-MS-OLK-FORCEINSPECTOROPEN:TRUE
BEGIN:VEVENT
CLASS:PUBLIC
UID:MEC-571962a69fe39e95c60ad4ba6ce2fa05@cmc.deusto.eus
DTSTART:20210714T140000Z
DTEND:20210714T150000Z
DTSTAMP:20251031T214000Z
CREATED:20251031
LAST-MODIFIED:20251031
PRIORITY:5
TRANSP:OPAQUE
SUMMARY:Learning to benchmark
DESCRIPTION:Speaker: Prof. Dr. Alfred Hero\nAffiliation: University of Michigan, USA\nOrganized by: FAU DCN-AvH, Chair for Dynamics, Control and Numerics – Alexander von Humboldt Professorship at FAU Erlangen-Nürnberg (Germany)\nZoom link\nMeeting ID: 699 8936 4767 | PIN code: 233558\nAbstract. We address the problem of learning an achievable lower bound on classification error from a labeled sample. We establish an optimization framework for this meta-learning problem, which we call benchmark learning. Benchmark learning leads to an accurate data-driven predictor of performance of a Bayes optimal classifier without having to construct the classifier and without assuming any parametric model for the data. The resultant predictor can be used to establish whether it is possible to improve classification performance of a specific classifier. It also yields a stopping rule for sequentially trained classifiers. In addition, The talk will cover relevant background, theory, algorithms, and applications of benchmark learning.\n \n\nJoin this event at LinkedIn\n\n \n
URL:https://cmc.deusto.eus/events-calendar/learning-to-benchmark/
CATEGORIES:FAU DCN-AvH Seminar
ATTACH;FMTTYPE=image/png:https://cmc.deusto.eus/wp-content/uploads/FAUDDS-DCNSeminar-14jul2021-alfredHero.png
END:VEVENT
END:VCALENDAR