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:20190719T085743Z
LOCATION:HG F 3
DTSTART;TZID=Europe/Stockholm:20190612T111500
DTEND;TZID=Europe/Stockholm:20190612T114500
UID:submissions.pasc-conference.org_PASC19_sess108_pap_jan130@linklings.co
m
SUMMARY:(mu, lambda)-CCMA-ES for Constrained Optimization with an Applicat
ion in Pharmacodynamics
DESCRIPTION:Paper\nComputer Science and Applied Mathematics, Life Sciences
\n\n(mu, lambda)-CCMA-ES for Constrained Optimization with an Application
in Pharmacodynamics\n\nArampatzis, Wälchli, Weber, Rästas, Koumoutsakos\n\
nWe present the algorithm CCMA, an extension to CMA-ES, an evolution strat
egy that has shown to perform well in a broad range of black-box optimizat
ion problems. The (mu,lambda)-CMA-ES effectively handles nonlinear nonconv
ex problems but faces difficulties in constrained optimization problems. W
e introduce viability boundaries and normal approximations to treat
inequality constraints and improve the search for an initial point not con
flicting with given constraints. We compare the performance of CCMA with a
state of the art optimization algorithm (mViE) showing favorable re
sults. Finally, CCMA is applied to a pharmacodynamics problem describing t
umor growth, and we demonstrate that the number of required model evaluati
ons is reduced by an order of magnitude when compared with a state of the
art optimization algorithm.
Full paper: https://doi.org/10.1145
/3324989.3325725
END:VEVENT
END:VCALENDAR