BEGIN:VCALENDAR
VERSION:2.0
PRODID:OpenCms 21.0.11
BEGIN:VTIMEZONE
TZID:Europe/Berlin
X-LIC-LOCATION:Europe/Berlin
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700329T020000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701025T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
END:STANDARD
END:VTIMEZONE				
BEGIN:VEVENT
DTSTAMP:20240604T093819
UID:69a1491a-2245-11ef-9ffb-000e0c3db68b
SUMMARY:Talk of Dr. Luca Furieri
DESCRIPTION:Dr. Luca Furieri\nSwiss Federal Institute of Technology in Lausanne\nLausanne, Switzerland&nbsp; &nbsp;\n\n&nbsp; \nTuesday 2024-06-11 4 p.m.\nIST Seminar Room 2.255 - Pfaffenwaldring 9 - Campus Stuttgart-Vaihingen&nbsp; \nAbstract\nAs we tackle complex optimization problems in engineering and computer science, developing\nalgorithms that converge faster and find better solutions is crucial. While control theory provides\noptimal worst-case convergence rates for convex functions, a recent trend in machine learning named\nLearning to Optimize&nbsp;(L2O) uses neural networks to discover update rules that excel in complex\nscenarios; the catch is, formal convergence guarantees are not available.&nbsp;Our research bridges\nthese two paradigms using nonlinear system theory. We introduce an unconstrained parametrization of\nall convergent algorithms for smooth, non-convex functions. Our framework is compatible with\nautomatic differentiation tools, ensuring convergence while learning to optimize over complex\nlandscapes.&nbsp;&nbsp; \nBiographical Information\nLuca Furieri is a Principal Investigator at EPF Lausanne since 2023. His research focuses on\noptimal control and optimization for distributed decision-making and large-scale cyber-physical\nsystems. Previously, he has been a Postdoctoral researcher at the Automatic Control Laboratory,\nEPFL. In 2020, he has been awarded a Ph.D. degree in Control and Optimization from ETH - Zurich. He\nhas received the SNSF Ambizione career grant in 2022, the IEEE Transactions on Control of Network\nSystems Best Paper Award in 2022, and the American Control Conference O. Hugo Schuck Best Paper\nAward in 2018.\n\n&nbsp;
DTSTART;TZID=Europe/Berlin;VALUE=DATE:20240611
URL;VALUE=URI:https://www.ist.uni-stuttgart.de/events/Talk-of-Dr.-Luca-Furieri/
END:VEVENT
END:VCALENDAR