BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
CALSCALE:GREGORIAN
PRODID:-//WordPress - MECv7.33.0//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-b7da6c184018c1c085e1e025ba678014@dcn.nat.fau.eu
DTSTART;TZID=Europe/Berlin:20260525T090000
DTEND;TZID=Europe/Berlin:20260529T170000
DTSTAMP:20251118T061331Z
CREATED:20251118
LAST-MODIFIED:20251203
PRIORITY:5
SEQUENCE:14
TRANSP:OPAQUE
SUMMARY:Mathematical Foundations of Machine Learning (MFML 2026)
DESCRIPTION:Event: MFML 2026, Mathematical Foundations of Machine Learning\nDate: Thu. May 25 – 29, 2026\nLecture: Machine Learning from an Applied Mathematician’s Perspective\nSpeaker: Prof. Enrique Zuazua, FAU – Friedrich-Alexander-Universität Erlangen-Nürnberg (Germany)\nAbstract. Machine Learning has emerged as one of the most transformative forces in contemporary science and technology. In this three-lecture series, I will discuss Machine Learning through the lens of applied mathematics, emphasizing its connections with control theory, partial differential equations, and numerical analysis. \nIn the first lecture, we will revisit the historical and conceptual links between Machine Learning and Systems Control (Cybernetics). This point of view allows us to reinterpret representation and expressivity properties of deep neural networks in terms of ensemble or simultaneous controllability of neural differential equations.  \nThe second lecture will focus on the use of neural network architectures as numerical approximation tools. We will consider, as a guiding example, the classical Dirichlet problem for the Laplace equation, formulated via energy minimization under neural-network constraints. Particular attention will be paid to the lack of convexity and coercivity in the resulting optimization problems. We will show how relaxation techniques may restore convexity at the price of losing coercivity, and we will discuss the mathematical implications of this trade-off for analysis and computation. \nIn the third lecture, we will present a PDE-based perspective on generative diffusion models. Their convergence can be reinterpreted in terms of the asymptotic behavior of Fokker–Planck equations driven by the so-called score vector field. We will explain how classical tools, such as Li-Yau-type differential inequalities for positive solutions of the heat equation, provide insight into the regularization and convergence properties of these models. \nThe series will conclude with a discussion of open problems and promising directions for future research at the interface of control theory, PDEs, numerical analysis, and modern Machine Learning.\nLecturers\n• Lénaïc Chizat. EPFL\n• Nicolás García-Trillos. University of Wisconsin-Madison\n• Guido Montúfar. UCLA | MPI-Leipzig\n• Enrique Zuazua. FAU\nWHEN\nThu. May 28, 2026 at HH:00H (local time)\nWHERE\nOn-site. The School will be hosted at:\nHotel Montana. Vason – Trento (Italy)\nOrganizers\nGian Paolo Leonardi. Department of Mathematics, University of Trento\nGiuseppe Savaré. Department of Decision Sciences, Bocconi University, Milan\nSee more at the official page of the event\n
URL:https://dcn.nat.fau.eu/events/mfml2026/
CATEGORIES:EZuazua,Seminar/Talk
ATTACH;FMTTYPE=image/png:https://dcn.nat.fau.eu/wp-content/uploads/MFML2026_EZuazua_may2026_img.png
END:VEVENT
END:VCALENDAR