BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
TZID:America/New_York
X-WR-TIMEZONE:America/New_York
BEGIN:VEVENT
UID:881@fds.yale.edu
DTSTART;TZID=America/New_York:20251112T113000
DTEND;TZID=America/New_York:20251112T130000
DTSTAMP:20251024T135616Z
URL:https://fds.yale.edu/events/fds-colloquium-george-lan-georgia-tech/
SUMMARY:FDS Colloquium: George Lan (Georgia Tech)\, "Algorithmic Foundation
 s of Risk-averse Optimization for Trustworthy AI"
DESCRIPTION:\nTalk summary: Over the past two decades\, stochastic optimiza
 tion has made remarkable strides\, driving its widespread adoption in mach
 ine learning (ML) and artificial intelligence (AI). However\, most existi
 ng models prioritize minimizing expected loss\, often leaving AI-driven de
 cisions vulnerable to costly or catastrophic failures and raising concern
 s about their trustworthiness in high-stakes applications. Risk-averse opt
 imization provides a principled approach to mitigating such vulnerabilitie
 s\, yet its adoption remains limited due to the lack of scalable and effi
 cient solution methods.\n\n\n\nIn this talk\, I will present the algorithm
 ic foundations of risk-averse optimization\, focusing on an important clas
 s of  \\(L_P\\) risk measures. I will introduce novel lifted reformulati
 ons that enhance tractability\, develop stochastic approximation algorithm
 s with provable convergence guarantees\, and establish fundamental comple
 xity limits. These advances provide a deeper theoretical understanding of
  risk-aware decision-making\, laying the groundwork for more robust and tr
 ustworthy AI systems.\n\n\n\nSpeaker bio: Guanghui (George) Lan is an A. 
 Russell Chandler III Chair and a professor in the H. Milton Stewart School
  of Industrial and Systems Engineering at the Georgia Institute of Techno
 logy. Prior to returning to Georgia Tech\, where he earned his Ph.D. in Au
 gust 2009\, Dr. Lan served on the faculty of the Department of Industrial
  and Systems Engineering at the University of Florida from 2009 to 2015. 
  His primary research interests lie in optimization\, machine learning\, 
 and reinforcement learning\, with applications in sustainability and healt
 hcare. His academic honors include the INFORMS Frederick W. Lanchester Pr
 ize (2023)\, the INFORMS Computing Society Prize (2022)\, the National Sc
 ience Foundation CAREER Award (2013)\, First Place in the INFORMS Junior F
 aculty Interest Group Paper Competition (2012)\, and recognition as a fin
 alist for the Mathematical Optimization Society Tucker Prize (2012).  Dr.
  Lan serves as an associate editor for Mathematical Programming\, SIAM Jou
 rnal on Optimization\, Operations Research\, and Computational Optimizatio
 n and Applications. He is also an associate director of the Center for Mac
 hine Learning at Georgia Tech.  Website.\n
CATEGORIES:Fellows Events,FDS Events,Colloquium
LOCATION:Yale Institute for Foundations of Data Science\, Kline Tower 13th 
 Floor\, Room 1327\, New Haven\, CT\, 06511\, United States
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=Kline Tower 13th Floor\, Ro
 om 1327\, New Haven\, CT\, 06511\, United States;X-APPLE-RADIUS=100;X-TITL
 E=Yale Institute for Foundations of Data Science:geo:0,0
END:VEVENT
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:STANDARD
DTSTART:20251102T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
END:STANDARD
END:VTIMEZONE
END:VCALENDAR