BEGIN:VCALENDAR VERSION:2.0 PRODID:-//wp-events-plugin.com//7.4.0.1//EN TZID:Europe/Paris X-WR-TIMEZONE:Europe/Paris BEGIN:VEVENT UID:395@isdm.umontpellier.fr DTSTART;TZID=Europe/Paris:20250123T140000 DTEND;TZID=Europe/Paris:20250123T140000 DTSTAMP:20260828T114732Z URL:https://isdm.umontpellier.fr/events/schur-s-positive-definite-network- deep-learning-in-the-spd-cone-with-structure-2/ SUMMARY:Schur's Positive-Definite Network: Deep Learning in the SPD cone wi th structure DESCRIPTION:Room 02.124\, Building 5\, St Priest campus\n\nMachine Learning in Montpellier\, Theory &\; Practice\n\nEstimating matrices in the sym metric positive-definite (SPD) cone is of interest for many applications r anging from computer vision to graph learning. While there exist various c onvex optimization-based estimators\, they remain limited in expressivity due to their model-based approach. The success of deep learning motivates the use of learning-based approaches to estimate SPD matrices with neural networks in a data-driven fashion. However\, designing effective neural ar chitectures for SPD learning is challenging\, particularly when the task r equires additional structural constraints\, such as element-wise sparsity. Current approaches either do not ensure that the output meets all desired properties or lack expressivity. We introduce SpodNet\, a novel and gener ic learning module that guarantees SPD outputs and supports additional str uctural constraints. Notably\, it solves the challenging task of learning jointly SPD and sparse matrices.\n\nMachine Learning in Montpellier\, Theo ry &\; Practice ATTACH;FMTTYPE=image/jpeg:https://isdm.umontpellier.fr/wp-content/uploads/ 2026/06/ml-mtp-gC78d5.png CATEGORIES:ML MTP LOCATION:Room 02.124 Building 5\, St Priest Campus\, Montpellier\, 34000\, France X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=St Priest Campus\, Montpell ier\, 34000\, France;X-APPLE-RADIUS=100;X-TITLE=Room 02.124 Building 5:geo :0,0 END:VEVENT BEGIN:VTIMEZONE TZID:Europe/Paris X-LIC-LOCATION:Europe/Paris BEGIN:STANDARD DTSTART:20241027T020000 TZOFFSETFROM:+0200 TZOFFSETTO:+0100 TZNAME:CET END:STANDARD END:VTIMEZONE END:VCALENDAR