BEGIN:VCALENDAR
CALSCALE:GREGORIAN
VERSION:2.0
METHOD:PUBLISH
PRODID:-//Drupal iCal API//EN
X-WR-TIMEZONE:America/New_York
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
DTSTART:20070311T020000
TZNAME:EDT
TZOFFSETTO:-0400
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
DTSTART:20071104T020000
TZNAME:EST
TZOFFSETTO:-0500
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
SEQUENCE:1
X-APPLE-TRAVEL-ADVISORY-BEHAVIOR:AUTOMATIC
UID:243596
DTSTAMP:20260930T110656Z
DTSTART;TZID=America/New_York:20261008T160000
DTEND;TZID=America/New_York:20261008T165000
URL;TYPE=URI:https://www.wpi.edu/news/calendar/events/ece-graduate-seminar-
 lecture-speaker-lili-liliana-su-northeastern-university
SUMMARY:ECE Graduate Seminar Lecture\, Speaker: Lili (Liliana) Su\, Northea
 stern University
DESCRIPTION:Title:\nTrustworthy Distributed Learning in Uncertain and Adver
 sarial Environments\nAbstract:\nDistributed learning enables large populat
 ions of devices and agents to collaboratively train machine learning model
 s without centralizing data. However\, real-world deployments must contend
  with unreliable communication\, intermittent participation\, system heter
 ogeneity\, privacy constraints\, and adversarial attacks. These challenges
  can significantly degrade the reliability\, efficiency\, and security of 
 existing learning algorithms.\nIn this talk\, I will present recent advanc
 es in designing provably robust distributed learning algorithms under such
  uncertainties. Specifically\, I will discuss methods for handling dynamic
  communication failures\, arbitrary participant unavailability\, and the j
 oint challenges of privacy preservation and adversarial robustness. Togeth
 er\, these results provide theoretical foundations and practical algorithm
 s for trustworthy distributed learning in uncertain and adversarial enviro
 nments.\n\n\nImage\n  \n\n\n\nSpeaker:\nLili (Liliana) Su\nAssistant Profe
 ssor\, Northeastern University\nBio:\nLili (Liliana) Su is an Assistant Pr
 ofessor at Northeastern University. Her research lies at the intersection 
 of machine learning\, distributed systems\, reinforcement learning\, and a
 utonomous systems\, with a focus on developing trustworthy AI that can lea
 rn\, adapt\, and operate reliably under uncertainty\, heterogeneity\, and 
 adversarial conditions. Her work has been supported by NSF\, ONR\, ARL\, A
 RPA-H\, and industry sponsors.\n\nHost: Professor John McNeill
END:VEVENT
END:VCALENDAR