BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//EventXplore//EN
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:895200b9-4e5f-409a-9869-51ee84701304@eventxplore
DTSTAMP:20260928T205622Z
DTSTART:20261006T173000Z
DTEND:20261006T183000Z
SUMMARY:MAE Colloquium: Frederike Dümbgen (Carnegie Mellon)
DESCRIPTION:Global Optimization for Robotics in the Age of Learning Optimization is the bedrock of robotics\, and robotics is a great stress test for optimization methods. High dimensionality\, nonconvexity\, and nonsmoothness make many robotics problems notoriously hard to solve\, whether with learning-based or model-based strategies. In this talk\, I will discuss our recent advances in bringing learning-based techniques together with optimization principles. First\, I will present extensions of moment-based optimization to data-driven\, nonparametric problems that retain partial global optimality guarantees. I
LOCATION:Kimball Hall
END:VEVENT
END:VCALENDAR