Bayesian-optimal design via interacting particle systems

Abstract : We propose a new stochastic algorithm for Bayesian-optimal design in nonlinear and high-dimensional contexts. Following Peter Muller, we solve an optimization problem by exploring the expected utility surface through Markov chain Monte Carlo simulations. The optimal design is the mode of this surface considered a probability distribution. Our algorithm relies on a "particle" method to efficiently explore high-dimensional multimodal surfaces, with simulated annealing to concentrate the samples near the modes. We first test the method on an optimal allocation problem for which the explicit solution is available, to compare its efficiency with a simpler algorithm. We then apply our method to a challenging medical case study in which an optimal protocol treatment needs to be determined. For this case, we propose a formalization of the problem in the framework of Bayesian decision theory, taking into account physicians' knowledge and motivations. We also briefly review further improvements and alternatives.
Document type :
Journal articles
Complete list of metadatas

https://hal-ineris.archives-ouvertes.fr/ineris-00963016
Contributor : Gestionnaire Civs <>
Submitted on : Friday, March 21, 2014 - 2:07:17 PM
Last modification on : Thursday, January 11, 2018 - 6:12:21 AM

Identifiers

Collections

Citation

Billy Amzal, Frédéric Y. Bois, Eric Parent, Christian P. Robert. Bayesian-optimal design via interacting particle systems. Journal of the American Statistical Association, Taylor & Francis, 2006, 101 (474), pp.773-785. ⟨10.1198/016214505000001159⟩. ⟨ineris-00963016⟩

Share

Metrics

Record views

255