BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VTIMEZONE
TZID:Europe/Vienna
BEGIN:DAYLIGHT
DTSTART:20170326T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20171029T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260429T074010Z
UID:5922989cbb27e995904974@ist.ac.at
DTSTART:20170523T140000
DTEND:20170523T150000
DESCRIPTION:Speaker: Anna Paola Muntoni\nhosted by Daniele De Martino\nAbst
 ract: Linear estimation (LE) models consist in the solutions of an under-d
 etermined system of equations with extra constraints. Many interesting pro
 blems arising from signal acquisitions and processing\, biology etc. are s
 tandardly modeled as LE. One of the most effective approaches relies on th
 e Bayesian inference\, where the original problem can be rephrased in a pr
 obabilistic framework. Here\, marginalizing the a posterioridistribution o
 f certain variables\, given a partial knowledge of the system\, provides t
 he key ingredient to determine a solution to a LE. Unfortunately\, in most
  of the cases\, these probability densities are difficult to estimate and 
 to marginalize as they would require impractical computations. In this tal
 k I will present an iterative algorithm\, the Expectation Propagation (EP)
  approximation\, that is able to accurately estimate marginal probability 
 densities of intractable distributions. EP is an approximation scheme deve
 loped in the computer science community as well as in statistical mechanic
 s with the name of Expectation Consistent. As a matter of example of the a
 dvantages carried by this method\, I will explain the problem of determini
 ng the feasible space of metabolic fluxes and I will compare EP results to
  the estimates of astate-of-the-art sampling technique\, Hit-and-Run Monte
  Carlo (HR). Not only EP is tremendously faster then HR\, but it is able t
 o accommodate additional constraints over fluxes (for instance\, fixing th
 e marginal probability of a specific flux to an experimental profile) with
 out affecting the computational cost.
LOCATION:Evolutionary Biology Room (I01.1OG - Zentralgebäude)\, ISTA
ORGANIZER:ddemarti@ist.ac.at
SUMMARY:Anna Paola Muntoni: Expectation Propagation for linear estimation m
 odels
URL:https://talks-calendar.ista.ac.at/events/631
END:VEVENT
END:VCALENDAR