Geometric MCMC for infinite-dimensional inverse problems
Bayesian inverse problems often involve sampling posterior distributions on infinite-dimensional function spaces. Traditional Markov chain Monte Carlo (MCMC) algorithms are characterized by deteriorating mixing times upon meshrefinement, when the finite-dimensional approximations become more accurat...
Main Authors: | Beskos, A, Girolami, M, Lan, S, Farrell, P, Stuart, A |
---|---|
Format: | Journal article |
Published: |
Elsevier
2016
|
Similar Items
-
Geometric problems in the theory of infinite-dimensional probability distributions /
by: 389604 Sudakov, V. N.
Published: (1979) -
MCMC for a hyperbolic Bayesian inverse problem in traffic flow modelling – ADDENDUM
by: Jeremie Coullon, et al.
Published: (2022-01-01) -
Trans-dimensional MCMC for Bayesian policy learning
by: Hoffman, M, et al.
Published: (2009) -
Bayesian Policy Learning with Trans−Dimensional MCMC
by: Hoffman, M, et al.
Published: (2007) -
Variational MCMC
by: de Freitas, N, et al.
Published: (2001)