BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium: OpAMP: Approximate Message Passing with Time-Varyin
 g Linear Operators
DTSTART:20261001T161500
DTEND:20261001T171500
DTSTAMP:20261001T160712Z
UID:d2063c36aebccdacdef155937eccadc04b660436da23d0f388666f59
CATEGORIES:Conferences - Seminars
DESCRIPTION:By: Bobak Nazer - Boston University\n\nAbstract\nApproximate
  message passing (AMP) is a powerful theoretical framework that provides p
 recise characterizations of iterative inference algorithms in the high-dim
 ensional regime\, including generalized linear regression and low-rank mat
 rix estimation as special cases. Implicitly\, the AMP framework presumes t
 hat computations (e.g.\, matrix multiplications) are carried out in a cent
 ralized fashion. However\, in practice\, due to time or memory constraints
 \, large-scale computations are often distributed across multiple servers\
 , some of which may respond more slowly than others (i.e.\, stragglers). W
 e demonstrate how to generalize AMP to allow for a time-varying linear ope
 rator to be applied to the data matrix at each iteration\, capturing erasu
 res due to missing partial computations as a special case. One surprising 
 consequence is that\, in certain applications\, scheduling partial computa
 tions can be more efficient in terms of total matrix multiplications. We i
 llustrate this phenomenon via a case study of power iteration applied to a
  spiked Wigner model. Joint work with Riccardo Rossetti and Galen Reeves.\
 n\nBio\nBobak Nazer is an Associate Professor in the Department of Electri
 cal and Computer Engineering at Boston University\, and is spending the 20
 26 - 2027 academic year on sabbatical at EPFL. He received the Ph.D. degre
 e in 2009 and the M.S. degree in 2005 from the University of California\, 
 Berkeley\, as well as the B.S. degree in 2003 from Rice University\, all i
 n electrical engineering. He is a past recipient of the IEEE Communication
 s Society & Information Theory Society Joint Paper Award\, the NSF CAREER 
 Award\, the Eli Jury Award\, and the Gerald and Deanne Gitner Family Award
  for Innovation in Teaching with Technology.\n\nMore information
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420 https://epfl.zoom.us/
 j/66735896236
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR