BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Robustness of accelerated first-order optimization algorithms
DTSTART:20250516T110000
DTEND:20250516T120000
DTSTAMP:20260530T213701Z
UID:6815868d10f72173fc3cf234bf4ae06c1ca1068a71530d74cf80687c
CATEGORIES:Conferences - Seminars
DESCRIPTION:Mihailo Jovanovic is a professor in the Ming Hsieh Department 
 of Electrical and Computer Engineering and the founding director of the Ce
 nter for Systems and Control at the University of Southern California\, US
 A.\n\nAbstract:\nGradient descent and its accelerated variants are increas
 ingly employed in learning and data-driven decision-making for uncertain d
 ynamical systems\, where gradients must be approximated through noisy meas
 urements. In this talk\, we draw on techniques from control theory to quan
 tify the robustness of accelerated first-order algorithms to stochastic un
 certainties in gradient evaluations. For unconstrained\, smooth\, and stro
 ngly convex problems\, we derive tight upper and lower bounds on the mean-
 square error of the optimization variable under additive white noise pertu
 rbations. Our analysis reveals fundamental tradeoffs between noise amplifi
 cation and convergence rates for any acceleration scheme with constant par
 ameters\, such as those in Nesterov's or heavy-ball methods. In particular
 \, we show that parameter choices enabling accelerated convergence in thes
 e methods necessarily lead to increased noise amplification compared to st
 andard gradient descent. To further elucidate these tradeoffs\, we provide
  a novel geometric characterization of linear convergence conditions for s
 trongly convex quadratic problems\, highlighting the interplay between con
 vergence rate\, noise sensitivity\, and algorithmic parameters. We then sp
 ecialize our results to distributed averaging over undirected networks\, e
 xamining how network size and topology influence the robustness of noisy a
 ccelerated algorithms.\n\nJoint work with: Hesameddin Mohammadi and Meisam
  Razaviyayn\n\n \n\nReferences:\n\nhttps://viterbi-web.usc.edu/~mihailo/p
 apers/mohrazjovTAC25.pdf\n\nhttps://viterbi-web.usc.edu/~mihailo/papers/mo
 hrazjovTAC21.pdf\n\n \n\nBiosketch:\n\nMihailo Jovanovic is a professor i
 n the Ming Hsieh Department of Electrical and Computer Engineering and the
  founding director of the Center for Systems and Control at the University
  of Southern California. He was a faculty member in the Department of Elec
 trical and Computer Engineering at the University of Minnesota\, Minneapol
 is\, from 2004 until 2017\, and has held visiting positions with Stanford 
 University\, the Simons Institute for the Theory of Computing\, the Instit
 ute for Mathematics and its Applications\, and the University of Belgrade.
  Professor Jovanovic received a CAREER Award from the National Science Fou
 ndation in 2007\, the George S. Axelby Outstanding Paper Award from the IE
 EE Control Systems Society in 2013\, and the Distinguished Alumnus Award f
 rom the University of California at Santa Barbara in 2014. He is a Fellow 
 of the American Physical Society (APS) and the Institute of Electrical and
  Electronics Engineers (IEEE).\n
LOCATION:ME C2 405 https://plan.epfl.ch/?room==ME%20C2%20405
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR