BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium: Scalable and Trustworthy Learning in Heterogeneous 
 Networks
DTSTART:20230323T120000
DTEND:20230323T130000
DTSTAMP:20260509T111034Z
UID:6284145a5ab0759f3bf866b5ac654d200c89f088bdd0206c19901669
CATEGORIES:Conferences - Seminars
DESCRIPTION:By: Tian Li - Carnegie Mellon University\nIC Faculty candidate
 \n\nAbstract\nTo build a responsible data economy and protect data ownersh
 ip\, it is crucial to enable learning models from separate\, heterogeneous
  data sources without data centralization. For example\, federated learnin
 g aims to train models across massive networks of remote devices or isolat
 ed organizations\, while keeping user data local. However\, federated netw
 orks introduce a number of unique challenges such as extreme communication
  costs\, privacy constraints\, and data and systems-related heterogeneity.
  \n\nMotivated by the application of federated learning\, my work aims to
  develop principled methods for scalable and trustworthy learning in heter
 ogeneous networks. In the talk\, I discuss how heterogeneity affects feder
 ated optimization\, and lies at the center of accuracy and trustworthiness
  constraints in federated learning. To address these concerns\, I present 
 scalable federated learning objectives and algorithms that rigorously acco
 unt for and directly model the practical constraints. I will also explore 
 trustworthy objectives and optimization methods for general ML problems be
 yond federated settings. \n\nBio\nTian Li is a fifth-year Ph.D. student i
 n the Computer Science Department at Carnegie Mellon University working wi
 th Virginia Smith. Her research interests are in distributed optimization\
 , federated learning\, and trustworthy ML. Prior to CMU\, she received her
  undergraduate degrees in Computer Science and Economics from Peking Unive
 rsity. She received the Best Paper Award at the ICLR Workshop on Security 
 and Safety in Machine Learning Systems\, was invited to participate in the
  EECS Rising Stars Workshop\, and was recognized as a Rising Star in Machi
 ne Learning/Data Science by multiple institutions.\n\nMore information
LOCATION:https://epfl.zoom.us/j/63813390249
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR