TY - JOUR
T1 - Maximum-entropy moment-closure for stochastic systems on networks
AU - Rogers, Tim
PY - 2011/5
Y1 - 2011/5
N2 - Moment-closure methods are popular tools to simplify the mathematical analysis of stochastic models defined on networks, in which high dimensional joint distributions are approximated (often by some heuristic argument) as functions of lower dimensional distributions. Whilst undoubtedly useful, several such methods suffer from issues of non-uniqueness and inconsistency. These problems are solved by an approach based on the maximisation of entropy, which is motivated, derived and implemented in this article. A series of numerical experiments are also presented, detailing the application of the method to the Susceptible-Infective-Recovered model of epidemics, as well as cautionary examples showing the sensitivity of moment-closure techniques in general.
AB - Moment-closure methods are popular tools to simplify the mathematical analysis of stochastic models defined on networks, in which high dimensional joint distributions are approximated (often by some heuristic argument) as functions of lower dimensional distributions. Whilst undoubtedly useful, several such methods suffer from issues of non-uniqueness and inconsistency. These problems are solved by an approach based on the maximisation of entropy, which is motivated, derived and implemented in this article. A series of numerical experiments are also presented, detailing the application of the method to the Susceptible-Infective-Recovered model of epidemics, as well as cautionary examples showing the sensitivity of moment-closure techniques in general.
UR - http://www.scopus.com/inward/record.url?scp=79958045826&partnerID=8YFLogxK
UR - http://dx.doi.org/10.1088/1742-5468/2011/05/P05007
UR - http://arxiv.org/abs/1103.4980
U2 - 10.1088/1742-5468/2011/05/P05007
DO - 10.1088/1742-5468/2011/05/P05007
M3 - Article
VL - 2011
JO - Journal of Statistical Mechanics-Theory and Experiment
JF - Journal of Statistical Mechanics-Theory and Experiment
SN - 1742-5468
IS - May
M1 - P05007
ER -