We propose a multi-resolution genetic algorithm that allows efficient
estimation of parameters in large-dimensional models. Such models
typically arise in modeling spatial phenomena. Fitting these models
often requires the use of complex numerical methods and large amounts
of computing power. Unfortunately, the numerical maximization and
sampling techniques used to fit such complex models often explore the
parameter space slowly resulting in unreliable estimates. Our
algorithm improves this exploration by incorporating elements of
simulated tempering into a genetic algorithm framework for
maximization. Our algorithm can also be adapted to perform Markov
chain Monte Carlo sampling from a posterior distribution in a Bayesian
setting, which can greatly improve mixing and exploration of the
posterior compared to ordinary MCMC methods. The proposed algorithm
can be used to estimate parameters in any model where the solution can
be solved on different scales, even if the data are not inherently
multi-scale. We address parallel implementation of the algorithms and
demonstrate their use on examples from groundwater hydrology.
Meet the speaker in Room 212 Cockins Hall at 4:30
p.m. Refreshments will be served.