BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:A Separation Principle for data-driven predictive control - the ro
 le of models and beyond
DTSTART:20250606T110000
DTEND:20250606T120000
DTSTAMP:20260407T101341Z
UID:82961eeeba95e2aadf82e303c1d1d9347029728fa026c7b66424e97d
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Alessandro Chiuso\, Ph.D. - IEEE Fellow\nAbstract\nIn t
 his talk I shall  discuss recent approaches to data-driven predictive con
 trol\, providing a bridge between behavioral and stochastic approachers. A
 s a byproduct I will formulate  a separation principle which elucidate th
 e role of models\, and their uncertainty in the control design problem\, 
 shedding light  on the model-free vs model-based dilemma. \n\nOur framew
 ork is constructive in the sense that\, not only  commonly used  regular
 ization follows from first principles\, but it also provides data-driven c
 losed form expressions for regularization terms\, thereby eliminating the 
 need for costly and often unrealistic tuning of hyper-parameters.  \n\nEx
 tensions to the time-varying/adaptive setup and non-linear predictive cont
 rol shall be discussed. \n\n \n\nShort Bio\nAlessandro Chiuso received h
 is Master degree (Laurea) in  1996\, from the University of Padova and th
 e PhD (Dottorato) in 2000 from the  University of Bologna. He has been lo
 ng term visitor with several international institutions\, among which  Wa
 shington University St. Louis\, KTH Stockholm\, UCLA\, ETH Zurich.  He jo
 ined the University of Padova  as an Assistant Professor in 2001\, Associ
 ate Professor in 2006 and then Full Professor since 2017. He currently ser
 ves as Editor (System Identification and Filtering) for Automatica. He has
  served as an Associate Editor for several prestigious journals (among whi
 ch Automatica\, IEEE Transactions on Automatic Control\, IEEE Transactions
  on Control Systems Technology\, European Journal of Control) and  has be
 en active in Conference organization (among with General Chair of SYSID 20
 21\, IPC co-chair of SYSID 2024).  He is a Fellow of IEEE (Class 2022). H
 is research interests are mainly at the intersection of Machine Learning\,
  Estimation\, Identification and Control.
LOCATION:ME C2 405 https://plan.epfl.ch/?room==ME%20C2%20405
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR