2000 character limit reached
Multilevel Monte Carlo in Approximate Bayesian Computation (1702.03628v1)
Published 13 Feb 2017 in stat.ME
Abstract: In the following article we consider approximate Bayesian computation (ABC) inference. We introduce a method for numerically approximating ABC posteriors using the multilevel Monte Carlo (MLMC). A sequential Monte Carlo version of the approach is developed and it is shown under some assumptions that for a given level of mean square error, this method for ABC has a lower cost than i.i.d. sampling from the most accurate ABC approximation. Several numerical examples are given.