BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:An approximate solution for the compressed sensing problem using s
tatistical mechanics tool
DTSTART:20230502T120000Z
DTEND:20230502T130000Z
DTSTAMP:20230923T103800Z
UID:indico-event-9820@indico.math.cnrs.fr
DESCRIPTION:Speakers: Anna Paola Muntoni (DISAT\, Polytechnic University o
f Turin\, Italy.)\n\nAbstract:Many interesting problems in fields ranging
from telecommunications to computational biology can be formalized in term
s of large underdetermined systems of linear equations with additional con
straints or regularizers. One of the most studied\, the compressed sensing
(CS) problem\, consists in finding the solution with the smallest number
of non-zero components of a given system of linear equations.In this talk\
, I will address the CS problem within a Bayesian inference framework wher
e the sparsity constraint is remapped into a singular prior distribution (
called Spike-and-Slab or Bernoulliâ€“Gauss). A solution to the problem is
attempted through the computation of marginal distributions via Expectatio
n Propagation\, an iterative computational scheme originally developed in
statistical physics.Keywords:compressed sensing\, expectation propagation\
, Bayesian inference\n\nhttps://indico.math.cnrs.fr/event/9820/
URL:https://indico.math.cnrs.fr/event/9820/
END:VEVENT
END:VCALENDAR