BEGIN:VCALENDAR
VERSION:2.0
PRODID:OpenCms 20.0.18
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:20221121T172345
UID:df20c968-69b8-11ed-a26d-000e0c3db68b
SUMMARY:Vortrag von Prof. Tobias Sutter
DESCRIPTION:Prof. Tobias Sutter\nDepartment of Computer and Information Science\nMachine Learning and Optimization\nUniversität Konstanz\nKonstanz, Germany\n  \nTuesday 2022-11-29 4 p.m.\nIST Seminar Room 2.255 - Pfaffenwaldring 9 - Campus Stuttgart-Vaihingen  \nAbstract\nGiven the recent progress in information technology with real-time data being available at large\nscale, many complex tasks involving dynamical environments are addressed via tools from machine\nlearning, control theory and optimization. While control theory in the past has mainly focused on\nmodel based design the advent of large scale data sets raises the possibility to analyse dynamical\nsystems on the basis of data rather than analytical models. From a machine learning perspective,\none of the main challenges going forward is to tackle problems involving dynamical systems which\nare beyond static pattern recognition problems. In this talk, I will give an overview about\ndifferent problems lying in this intersection of dynamical systems, learning and control that I\nhave worked on in the past. In particular, I will discuss how to efficiently learn a linear\ndynamical system with stability guarantees and how to identify its topological equivalence class\nbased on a single trajectory of correlated data.  \nBiographical Information\nTobias Sutter received a B.Sc. and M.Sc. degree in Mechanical Engineering in 2010 and 2012 from\nETH Zürich, and a Ph.D. degree in Electrical Engineering at the Automatic Control Laboratory, ETH\nZürich in 2017. He currently is an Assistant Professor at the Computer Science Department in\nKonstanz, Germany. Prior to joining University of Konstanz, he held a research and lecturer\nappointment with EPFL at the Chair of Risk Analytics and Optimization and at the Institute of\nMachine Learning at ETH Zürich. His research interests revolve around control, reinforcement\nlearning and data-driven robust optimization. He was a recipient of the 2016 George S. Axelby\nOutstanding Paper Award from the IEEE Control Systems Society and received the ETH Medal for his\noutstanding Ph.D. thesis on approximate dynamic programming in 2018.\n   
DTSTART;TZID=Europe/Berlin;VALUE=DATE:20221129
URL;VALUE=URI:https://www.ist.uni-stuttgart.de/de/veranstaltungen/Vortrag-von-Prof.-Tobias-Sutter/
END:VEVENT
END:VCALENDAR