BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
CALSCALE:GREGORIAN
PRODID:-//WordPress - MECv7.32.0//EN
X-ORIGINAL-URL:https://dcn.nat.fau.eu/
X-WR-CALNAME:
X-WR-CALDESC:FAU DCN-AvH. Chair for Dynamics, Control, Machine Learning and Numerics -Alexander von Humboldt Professorship
X-WR-TIMEZONE:Europe/Berlin
BEGIN:VTIMEZONE
TZID:Europe/Berlin
X-LIC-LOCATION:Europe/Berlin
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20260329T030000
RRULE:FREQ=YEARLY;BYMONTH=03;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20261025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=4SU
END:STANDARD
END:VTIMEZONE
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-PUBLISHED-TTL:PT1H
X-MS-OLK-FORCEINSPECTOROPEN:TRUE
BEGIN:VEVENT
CLASS:PUBLIC
UID:MEC-465c005d04204f859d0080c915f744b3@dcn.nat.fau.eu
DTSTART;TZID=Europe/Berlin:20250428T090000
DTEND;TZID=Europe/Berlin:20250430T170000
DTSTAMP:20241209T112655Z
CREATED:20241209
LAST-MODIFIED:20251008
PRIORITY:5
SEQUENCE:4
TRANSP:OPAQUE
SUMMARY:Machine Learning and PDEs Workshop #MLPDES25
DESCRIPTION:*The recordings are available at: https://mod.fau.eu/mlpdes25/\n \nOn April 28 – 30, 2025, our FAU MoD ( http://www.mod.fau.eu ), Research Center for Mathematics of Data is hosting the “Machine Learning and PDEs” workshop (MLPDES25) supported by the FAU DCN-AvH, Chair for Dynamics, Control, Machine Learning and Numerics, the AFOSR, Air Force Office of Scientific Research, PoliBa, Politecnico di Bari and the Alexander von Humboldt Stiftung/Foundation organized from April 28 to 30, 2025 at FAU, Friedrich-Alexander-Universität Erlangen-Nürnberg in Erlangen – Bavaria (Germany).\nThis international workshop brings together researchers from across Europe and the United States to explore the growing connection between Machine Learning (ML) and Partial Differential Equations (PDEs)—two core fields in modern mathematics that are now developing a dynamic, mutually beneficial relationship. ML methods are increasingly used to simulate and solve complex PDEs, such as those found in bio-mathematics and fluid dynamics. Meanwhile, techniques from PDE and control theory are helping us better understand and improve ML models.\n #MLPDES25 @YouTube: Watch the spot (short) | Video teaser\nWith participants from diverse backgrounds, this event aims to establish a collaborative platform for experts to network, share insights, and drive progress in this exciting field. We’ll dive into recent theoretical advancements and applications, while also discussing ongoing challenges in areas such as:\n• Control and PDE methods for universal approximation and data classification\n• Mean field analysis of neural networks\n• ML applications in traffic flow modeling and autonomous driving\n• ML and numerical simulation in bio-mechanics and micro-fluidics\nJoin us as we bridge these fields, focusing on both foundational research and practical applications.\nREGISTRATION\nRegistration is closed.\n*After the event, an attendance certificate will be sent by email (Non-academic credits).\n\nPoster of the #MLPDES25\n \nSPEAKERS\n\n• Paola Antonietti. Politecnico di Milano\nLecture: Machine learning enhanced polytopal finite element methods for neurodegenerative disorder modeling\n\n• Alessandro Coclite. Politecnico di Bari\nLecture: Replicator dynamics on a network\n\n• Fariba Fahroo. Air Force Office of Scientific Research\nLecture: International grant opportunities and research interests of the Air Force Office of Scientific Research\n\n• Giovanni Fantuzzi. FAU MoD/DCN-AvH, Friedrich-Alexander-Universität Erlangen-Nürnberg\nLecture: Exact sequence classification with hardmax transformers\n\n• Borjan Geshkovski. Inria, Sorbonne Université\nLecture: Many-particle systems perspective on Transformers\n\n• Paola Goatin. Inria, Sophia-Antipolis\nLecture: Modern calibration strategies for macroscopic traffic flow models\n\n• Shi Jin.  SJTU, Shanghai Jiao Tong University\nLecture: Allen-Cahn message passing in graph neural networks and fast Sinkhorn for Wasserstein-1 metric\n\n• Alexander Keimer. Universität Rostock\nLecture: Optimal control of nonlocal conservation laws and the singular limit\n\n• Felix J. Knutson. Air Force Office of Scientific Research\nLecture: International grant opportunities and research interests of the Air Force Office of Scientific Research\n\n• Anne Koelewijn. FAU MoD / BioMAC. Friedrich-Alexander-Universität Erlangen-Nürnberg\nLecture: SSPINNpose: Self-supervised learning of biomechanical variables without ground truth\n\n• Günter Leugering.  FAU MoD, Friedrich-Alexander-Universität Erlangen-Nürnberg\nLecture: The Speinshart Scientific Center for AI and Supertech\n\n• Camilla Nobili. University of Surrey\nLecture: Quantification of enhanced dissipation and mixing for time-dependent shear flows\n\n• Gianluca Orlando. Politecnico di Bari\nLecture: Replicator dynamics as the large-population limit of a multi-strategy discrete moran process\n\n• Michele Palladino. Università degli Studi dell’Aquila\nLecture: Handling uncertainty in optimal control\n\n• Gabriel Peyré. CNRS, ENS-PSL\nLecture: Transformers are universal in-context learners\n\n• Alessio Porretta. Università di Roma Tor Vergata\nLecture: Diffusion effects in optimal transport and mean-field planning models\n\n• Francesco Regazzoni. Politecnico di Milano\nLecture: Discovering the hidden low-dimensional dynamics of time-dependent PDEs with latent dynamics networks\n\n• Domènec Ruiz-Balet. Université Paris Dauphine\nLecture: Some remarks on matching measures with Machine Learning architectures\n\n• Daniel Tenbrinck. FAU, Friedrich-Alexander-Universität Erlangen-Nürnberg\nLecture: Eigenvalue problems on graphs and hypergraphs\n\n• Daniela Tonon. Università di Padova\nLecture: Hamilton-Jacobi equations on infinite dimensional spaces\n\n• Juncheng Wei. Chinese University of Hong Kong\nLecture: On Brezis’s first open problem: a complete solution\n\n• Yaoyu Zhang. Shanghai Jiao Tong University\nLecture: The condensation phenomenon of Deep Neural Networks\n\n• Wei Zhu. Georgia Institute of Technology\nLecture: Structure-Preserving Machine Learning and Data-Driven structure discovery\n \nAUDIENCE\nThis is a hybrid event (On-site/online) open to: Public, Students, Postdocs, Professors, Faculty, Alumni and the scientific community all around the world.\n \nPROGRAM\n#MLPDE25 Program details\n#MLPDE25 Schedule\n\n \nWHEN\nMon. – Wed. April 28 – 30, 2025 • 09:30H – 17:00H\nThis event at your local time\n \nWHERE\nOn-site / Online\n[On-site] FAU, Friedrich-Alexander-Universität Erlangen-Nürnberg\nSenatssaal (Senate Hall) im Kollegienhaus\nUniversitätsstraße 15, 91054\nErlangen – Bavaria, Germany\nHow to get to Erlangen?\n[Online] Live-streaming\nhttps://www.fau.tv/fau-mod-livestream-2025\n \nScientific Committee\n• Giuseppe Maria Coclite ( https://sites.google.com/site/coclitegm/homepage-of-giuseppe-maria-coclite ). Politecnico di Bari\n• Enrique Zuazua ( https://dcn.nat.fau.eu/zuazua ). FAU MoD/DCN-AvH, Friedrich-Alexander-Universität Erlangen-Nürnberg\n \nOrganizing Committee\n• Darlis Bracho Tudares ( https://dcn.nat.fau.eu/darlis-bracho-tudares ). FAU MoD/DCN-AvH, Friedrich-Alexander-Universität Erlangen-Nürnberg\n• Nicola De Nitti ( https://dcn.nat.fau.eu/nicola-de-nitti/ ). Università di Pisa\n• Lorenzo Liverani ( https://dcn.nat.fau.eu/lorenzo-liverani/ ). FAU DCN-AvH, Friedrich-Alexander-Universität Erlangen-Nürnberg\n\nPoster of the #MLPDES25\n #MLPDES25 @YouTube: Watch the spot (short / teaser)\nThis event @LinkedIn\n \nYou might like:\n• Upcoming events\n• FAU MoD Lectures\n• FAU MoD Courses & Workshops\n  \n_\nDon’t miss out our last news and connect with us!\nLinkedIn | X (Twitter) | Instagram | YouTube | Bluesky\n
URL:https://dcn.nat.fau.eu/events/mlpdes25/
ORGANIZER;CN=AFOSR:MAILTO:
CATEGORIES:Conference,EZuazua,FAU MoD workshop,FAU-DCN Workshop,Seminar/Talk,Workshop
LOCATION:Erlangen - Bavaria, Germany
ATTACH;FMTTYPE=image/png:https://dcn.nat.fau.eu/wp-content/uploads/FAUMoD_MLPDES25_april2025_img.png
END:VEVENT
END:VCALENDAR