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:20221222T164241
UID:454f0424-820f-11ed-9c5d-000e0c3db68b
SUMMARY:Vortrag von Prof. Andrea Iannelli
DESCRIPTION:Prof. Andrea Iannelli\nInstitute for Systems Theory and Automatic Control\nUniversity of Stuttgart\nStuttgart, Germany\n  \nTuesday 2023-01-10 4 p.m.\nIST Seminar Room 2.255 - Pfaffenwaldring 9 - Campus Stuttgart-Vaihingen  \nAbstract\nThe increase in systems complexity caused by societal challenges and the push to address\nincreasing challenging tasks makes the synthesis of actions to achieve certain closed-loop system’s\nperformance a sequential decision making problem under uncertainty. This motivates us to rethink\nthe standard paradigm in control design of synthesizing the control algorithm offline (e.g. a\nmatrix of transfer functions as in loop-shaping or a static map between measured state and input as\nin model predictive control).\nIn this work we will present our on-going work towards framing control of adaptive systems in\nchanging environments as an online learning problem, whereby the decision-maker takes sequential\ndecisions by solving a series of time-varying optimization problems having a-priori only partial\nknowledge of the cost functions. On the one hand, the online learning viewpoint inherently takes\ninto account the time-varying and uncertain nature of the problem. On the other hand, it considers\na different performance metric than the others used in system theory and control, i.e. regret,\nwhich measures the accumulated suboptimality with respect to a clairvoyant decision maker.\nMotivated by the goal to understand what online learning, traditionally used in game-theoretic\nor decision-making problems which have no dynamics, can offer in the context of systems theory and\ncontrol, we analyse two classic control problems, i.e. Iterative Learning Control and control, from\nthis viewpoint. Our findings show that regret characterizes fundamental limitations of non-adaptive\nalgorithms (for the former) and captures the robustness associated with planning for the worst-case\n(for the latter).  \nBiographical Information\nAndrea Iannelli is a tenure-track junior professor in the Institute for Systems Theory and\nAutomatic Control (IST) at the University of Stuttgart (Germany). Andrea's main research interests\nare at the intersection of control theory, optimization, and learning, with a particular focus on\noptimization-based control methods, system identification, uncertainty quantification, and\nsequential decision making problems. He obtained the Bachelor and Master degrees in Aerospace\nEngineering at the University of Pisa (Italy). In April 2019 he completed his PhD at the University\nof Bristol (UK), funded by the H2020 project FLEXOP, where he focused on the reconciliation between\nrobust control theory and dynamical systems approaches, with application to uncertain aerospace\nsystems. From May 2019 to September 2022 he was a PostDoctoral researcher in the Automatic Control\nLaboratory (IfA) at ETH Zürich (Switzerland). During his PostDoc he has been developing and\ndemonstrating theoretical advances in data-driven control theory, optimization-based control, and\nsystem identification, with particular emphasis on the use of data to make reliable predictions and\ndecisions.\n   
DTSTART;TZID=Europe/Berlin;VALUE=DATE:20230110
URL;VALUE=URI:https://www.ist.uni-stuttgart.de/de/veranstaltungen/Vortrag-von-Prof.-Andrea-Iannelli/
END:VEVENT
END:VCALENDAR