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-45b531e01616fe0a6b2d8d51583b36a7@dcn.nat.fau.eu
DTSTART;TZID=Europe/Berlin:20241119T163000
DTEND;TZID=Europe/Berlin:20241119T173000
DTSTAMP:20241014T194703Z
CREATED:20241014
LAST-MODIFIED:20241014
PRIORITY:5
SEQUENCE:8
TRANSP:OPAQUE
SUMMARY:PGMODAYS 2024: Universal Approximation of Dynamical Systems by Semi-Autonomous Neural ODEs
DESCRIPTION:On Tue. November 19, 2024, Kang Liu will talk on “Universal Approximation of Dynamical Systems by Semi-Autonomous Neural ODEs” at the PGMODAYS 2024 (Session 9B) at the FMJH – Fondation Mathématique Jacques Hadamard organized on November 19 – 20, 2024 at University of Paris-Saclay in France.\nSession 9B: Invited Session: Differential equations in machine learning\nKang Liu, Ziqian Li, Lorenzo Liverani and Enrique Zuazua\nUniversal Approximation of Dynamical Systems by Semi-Autonomous Neural ODEs\nPRESENTER: Kang Liu\nhttps://easychair.org/smart-program/PGMODAYS2024/2024-11-19.html#talk:270414\nAbstract. In this presentation, we introduce semi-autonomous neural ordinary differential equations (SA-NODEs), a variation of the classical NODEs, employing fewer parameters. We investigate the universal approximation properties of SA-NODEs for dynamical systems from both a theoretical and a numerical perspective. Within the assumption of a finite-time horizon, under general hypotheses we establish an asymptotic approximation result, demonstrating that the error vanishes as the number of parameters goes to infinity. Under additional regularity assumptions, we further specify this convergence rate in relation to the number of parameters, utilizing quantitative approximation results in the Barron space. Based on the previous result, we prove an approximation rate for transport equations by their neural counterparts. Our numerical experiments validate the effectiveness of SA-NODEs in capturing the dynamics of various ODE systems and transport equations. Additionally, we compare SA-NODEs with classical NODEs, highlighting the superior performance and reduced complexity of our approach.\nInvited plenary speakers\n• Paola Goatin (Inria Sophia-Antipolis. France)\n• Edouard Graves (LLM, Kyutai. France)\n• Huseyin Topaoglou (Cornell University. USA)\n• Enrique Zuazua (FAU, Erlangen. Germany)\nRegistration\nRegistration and abstract submission deadline date: September 13, 2024.\nSee about submission details\nConference fees may apply. See more at the official page of the event.\nWHEN\nTue. November 19, 2024 at 16:30H\nWHERE\nEDF Lab Paris-Saclay, Palaiseau, France\nCheck the official page of the event\n\n
URL:https://dcn.nat.fau.eu/events/pgmodays-2024-universal-approximation-of-dynamical-systems-by-semi-autonomous-neural-odes/
CATEGORIES:EZuazua,Seminar/Talk,Workshop
END:VEVENT
END:VCALENDAR