BEGIN:VCALENDAR
VERSION:2.0
PRODID:-// - ECPv6.15.15//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://isdm.umontpellier.fr
X-WR-CALDESC:Évènements pour 
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20240331T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20241027T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20250330T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20251026T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20260329T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20261025T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Paris:20250217T160000
DTEND;TZID=Europe/Paris:20250217T160000
DTSTAMP:20260502T030307
CREATED:20250603T090116Z
LAST-MODIFIED:20250603T090116Z
UID:7063-1739808000-1739808000@isdm.umontpellier.fr
SUMMARY:Rethinking Early Stopping: Refine\, Then Calibrate
DESCRIPTION:Inria Montpellier\, St-Priest Campus\, Building 5\, Room 02/022\nMachine Learning in Montpellier\, Theory & Practice \nMachine learning classifiers often produce probabilistic predictions that are critical for accurate and interpretable decision-making in various domains. The quality of these predictions is generally evaluated with proper losses like cross-entropy\, which decompose into two components: calibration error assesses general under/overconfidence\, while refinement error measures the ability to distinguish different classes.\nIn this paper\, we provide theoretical and empirical evidence that these two errors are not minimized simultaneously during training. Selecting the best training epoch based on validation loss thus leads to a compromise point that is suboptimal for both calibration error and\, mostimportantly\, refinement error. To address this\, we introduce a new metric for early stopping and hyperparameter tuning that makes it possible to minimize refinement error during training. The calibration error is minimized after training\, using standard techniques. Our method integrates seamlessly with any architecture and consistently improves performance across diverse classification tasks. \n            Visio\n                        Article
URL:https://isdm.umontpellier.fr/event/rethinking-early-stopping-refine-then-calibrate/
CATEGORIES:Séminaire
ATTACH;FMTTYPE=image/jpeg:https://isdm.umontpellier.fr/wp-content/uploads/2025/02/ml-mpt-1.jpg
END:VEVENT
END:VCALENDAR