BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20210916T132447Z
LOCATION:Lise Girardin
DTSTART;TZID=Europe/Stockholm:20210709T123000
DTEND;TZID=Europe/Stockholm:20210709T130000
UID:submissions.pasc-conference.org_PASC21_sess190_pap_dec103@linklings.co
 m
SUMMARY:Load Balancing in Large Scale Bayesian Inference
DESCRIPTION:Paper\n\nLoad Balancing in Large Scale Bayesian Inference\n\nW
 aelchli, Martin, Economides, Amoudruz, Arampatzis...\n\nWe present a novel
  strategy to improve load balancing for large scale Bayesian inference pro
 blems. Load imbalance can be particularly destructive in generation based 
 uncertainty quantification (UQ) methods since all compute nodes in a large
 -scale allocation have to synchronize after every generation and therefore
  remain in an idle state until the longest model evaluation finishes. Our 
 strategy relies on the concurrent scheduling of independent Bayesian infer
 ence experiments while sharing a group of worker nodes, reducing the destr
 uctive effects of workload imbalance in population-based sampling methods.
  <br /><br />To demonstrate the efficiency of our method, we apply it to i
 nfer parameters of a red blood cell (RBC) model. We perform a data-driven 
 calibration of the RBC's membrane viscosity by applying hierarchical Bayes
 ian inference methods. To this end, we employ a computational model to sim
 ulate the relaxation of an initially stretched RBC towards its equilibrium
  state. The results of this work advance upon the current state of the art
  towards realistic blood flow simulations by providing inferred parameters
  for the RBC membrane viscosity.<br /><br />We show that our strategy achi
 eves a notable reduction in imbalance and significantly improves effective
  node usage on 512 nodes of the CSCS Piz Daint supercomputer. Our results 
 show that, by enabling multiple independent sampling experiments to run co
 ncurrently on a given allocation of supercomputer nodes, our method sustai
 ns a high computational efficiency on a large-scale supercomputing setting
 .\n\nDomain: CS and Math, Physics, Life Sciences
END:VEVENT
END:VCALENDAR