BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/New_York BEGIN:DAYLIGHT DTSTART:20240310T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:EDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20241103T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20241023T192625Z UID:143AA388-7FA8-45C1-B0D9-531CFC1D9FBF DTSTART;TZID=America/New_York:20241023T120000 DTEND;TZID=America/New_York:20241023T130000 DESCRIPTION:Distributed control is a classical research topic. While a rich theory is available\, some assumptions such as availability of subsystem dynamics and topology and the subsystems following the prescribed controll ers exactly have proven difficult to remove. An interesting direction in r ecent times to get away from these assumptions has been the utilization of learning for control. In this talk\, we consider some problems in control design for distributed systems using learning. Our core message is that u tilizing control-relevant properties in learning algorithms can not only g uarantee concerns such as stability\, performance\, safety\, and robustnes s that are important in control of physical systems\, but also help with i ssues such as data sparsity and sample complexity that are concerns during the implementation of learning algorithms.\n\nCo-sponsored by: Temple Uni versity Electrical and Computer Engineering Department\n\nSpeaker(s): Vija y\, \n\nVirtual: https://events.vtools.ieee.org/m/432380 LOCATION:Virtual: https://events.vtools.ieee.org/m/432380 ORGANIZER:ziauddin.ahmad.us@ieee.org SEQUENCE:30 SUMMARY:LEARNING-BASED DISTRIBUTED CONTROL URL;VALUE=URI:https://events.vtools.ieee.org/m/432380 X-ALT-DESC:Description: <br /><p class="MsoNormal" style="text-align: justi fy\;"><span style="font-size: 11.0pt\;">Distributed control is a classical research topic. While a rich theory is available\, some assumptions such as availability of subsystem dynamics and topology and the subsystems foll owing the prescribed controllers exactly have proven difficult to remove. An interesting direction in recent times to get away from these assumption s has been the utilization of learning for control. In this talk\, we cons ider some problems in control design for distributed systems using learnin g. Our core message is that utilizing control-relevant properties in learn ing algorithms can not only guarantee concerns such as stability\, perform ance\, safety\, and robustness that are important in control of physical s ystems\, but also help with issues such as data sparsity and sample comple xity that are concerns during the implementation of learning algorithms.</ span></p> END:VEVENT END:VCALENDAR