BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Causal Representation Learning - Prof. Ali Tajer\, Rensselaer Poly
 technic Institute ​
DTSTART:20250508T140000Z
DTEND:20250508T150000Z
UID:TALK229711@talks.cam.ac.uk
CONTACT:Ramji Venkataramanan
DESCRIPTION:Machine learning (ML) has shown great success in learning low-
 dimensional and semantically interpretable representations of high-dimensi
 onal data. Recent leaps in designing transformers have further proliferate
 d representation learning. Despite such success\, strong generalization 
 — transfer of the learned representations to new problems — is still a
 n unsolved problem.  Addressing strong representation requires moving away
  from learning good enough representations to learning ground truth repres
 entation. As a key step toward strong generalization\, causal representati
 on learning (CRL) has emerged as a cutting-edge field that merges the stre
 ngths of statistical inference\, machine learning\, and causal inference. 
 Its objective is to estimate the ground truth latent representation of the
  data and the rich structures that model the interactions among the variab
 les in the latent space.\n\nIn this talk\, we will explore the latest adva
 ncements in the emerging field of CRL. We will introduce the foundational 
 concepts and motivations behind combining representation learning with cau
 sal inference. Following a brief history of CRL\, we will describe its pri
 mary objectives and the theoretical challenges. We will then review the ke
 y approaches to address these challenges\, including CRL with multi-view o
 bservations\, CRL with interventions on latent variables\, and CRL applied
  to temporal data. We will also highlight real-world application opportuni
 ties\, discuss the challenges in scaling CRL to practical use cases\, and 
 discuss open questions for CRL related to theoretical and empirical viewpo
 ints.\n\n\n*Bio*: Ali Tajer received a B.Sc. and an M.Sc. degree in Electr
 ical Engineering from Sharif University of Technology\, an M.A. in Statist
 ics\, and a Ph.D. in Electrical Engineering from Columbia University. Duri
 ng 2010-2012\, he was a Postdoctoral Research Associate at Princeton Unive
 rsity. He is currently a Professor of Electrical\, Computer\, and Systems 
 Engineering at Rensselaer Polytechnic Institute. His research interests in
 clude mathematical statistics\, machine learning\, and information theory.
  He is currently an Associate Editor for the IEEE Transactions on Informat
 ion Theory and a Senior Area Editor for the IEEE Transactions on Signal Pr
 ocessing. In the past\, he has served as an Associate Editor for the IEEE 
 Transactions on Signal Processing\, an Editor for the IEEE Transactions on
  Communications\, and a Guest Editor for the IEEE Signal Processing Magazi
 ne. He received the Jury Award (Columbia University)\, School of Engineeri
 ng Research Excellence Award for Junior Faculty (Rensselaer)\, School of E
 ngineering Classroom Excellence Award (Rensselaer)\, James M. Tien '66 Ear
 ly Career Award for Faculty (Rensselaer)\, School of Engineering Classroom
  Excellence Award for Senior Faculty (Rensselaer)\, a CAREER award from th
 e U.S. National Science and a U.S. Air Force Fellowship Award. He is a mem
 ber of the 2025-2026 class of Distinguished Lecturers of the IEEE Informat
 ion Theory Society.\n
LOCATION:JDB Seminar Room\, CUED
END:VEVENT
END:VCALENDAR