BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Pick-to-Learn for Systems and Control: Data-driven design with sta
 te-of-the art safety guarantees
DTSTART:20250616T150000
DTEND:20250616T160000
DTSTAMP:20260407T111357Z
UID:fc11f75e0d2134fa4c7d9600b7b9f633a53fb174efde7d00681ae706
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof Dario Paccagnan\, \n\nAssociate Professor at the Depart
 ment of Computing\,\n\nImperial College London\, UK\nABSTRACT:  Data-driv
 en methods have become powerful tools for tackling increasingly complex pr
 oblems in Systems and Control. However\, deploying these methods in real-w
 orld settings —  especially safety-critical ones —  requires rigorou
 s safety and performance guarantees. This need has motivated much recent w
 ork at the interface of Statistical Learning and Control\, aiming to integ
 rate formal guarantees with data-driven design methods. However\, many exi
 sting approaches achieve this only by sacrificing valuable data for testin
 g/calibration or by restricting the design space\, thus leading to subopti
 mal performances.\n\nAgainst this backdrop\, in this talk I will introduce
  Pick-to-Learn (P2L) for Systems and Control\, a novel framework designed
  to equip any data-driven control method with state-of-the-art safety an
 d performance guarantees. Crucially\, P2L enables the use of all available
  data to jointly synthesize and certify the design\, eliminating the nee
 d to set aside data for calibration or validation purposes.\n\nI will then
  demonstrate how\, as a result\, P2L delivers designs and certificates tha
 t outperforms existing methods across a range of core problems including o
 ptimal control\, reachability analysis\, safe synthesis\, and robust contr
 ol.\n\nBIOGRAPHY: Prof Dario Paccagnan is an Associate Professor at the De
 partment of Computing\, Imperial College London where he joined in the Fal
 l 2020. Before that\, he was a postdoctoral fellow at the University of Ca
 lifornia\, Santa Barbara. He obtained his PhD from the Automatic Control L
 aboratory\, ETH Zurich\, Switzerland\, in 2018. He received a B.Sc. and M.
 Sc. in Aerospace Engineering from the University of Padova\, Italy\, in 20
 11 and 2014\, and a M.Sc. in Mathematical Modelling and Computation from t
 he Technical University of Denmark in 2014\; all with Honors. Prof. Dario 
 Paccagnan's interests are at the interface of game theory\, control theory
 \, and learning theory with a focus on tackling societal-scale challenges.
  He was a finalist for the 2019 EECI best PhD thesis award and was recogni
 zed with the SNSF Early Postdoc Mobility Fellowship\, the SNSF Doc Mobilit
 y Fellowship\, and the ETH medal for his doctoral work. He is the recipien
 t of the best student paper award (as advisor) at AISTAT 2025.
LOCATION:ME C2 405 https://plan.epfl.ch/?room==ME%20C2%20405
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR