Expectation Propogation for approximate inference in dynamic Bayesian networks [article]

Tom Heskes, Onno Zoeter
2012 arXiv   pre-print
We describe expectation propagation for approximate inference in dynamic Bayesian networks as a natural extension of Pearl s exact belief propagation.Expectation propagation IS a greedy algorithm, converges IN many practical cases, but NOT always.We derive a DOUBLE - loop algorithm, guaranteed TO converge TO a local minimum OF a Bethe free energy.Furthermore, we show that stable fixed points OF (damped) expectation propagation correspond TO local minima OF this free energy, but that the
more » ... need NOT be the CASE .We illustrate the algorithms BY applying them TO switching linear dynamical systems AND discuss implications FOR approximate inference IN general Bayesian networks.
arXiv:1301.0572v1 fatcat:rzeyzwcj5ff4bf35a5csdylhea