Free energy methods for Bayesian inference: efficient exploration of univariate Gaussian mixture posteriors

@article{Chopin2012FreeEM,
  title={Free energy methods for Bayesian inference: efficient exploration of univariate Gaussian mixture posteriors},
  author={Nicolas Chopin and Tony Leli{\`e}vre and Gabriel Stoltz},
  journal={Statistics and Computing},
  year={2012},
  volume={22},
  pages={897-916}
}
Because of their multimodality, mixture posterior distributions are difficult to sample with standard Markov chain Monte Carlo (MCMC) methods. We propose a strategy to enhance the sampling of MCMC in this context, using a biasing procedure which originates from computational Statistical Physics. The principle is first to choose a “reaction coordinate”, that is, a “direction” in which the target distribution is multimodal. In a second step, the marginal log-density of the reaction coordinate… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-10 of 35 references

From Microphysics to Macrophysics

  • R. Balian
  • Methods and Applications of Statistical Physics…
  • 2007
Highly Influential
4 Excerpts

Free Energy Computations: A Mathematical Perspective

  • T. Lelièvre, M. Rousset, G. Stoltz
  • 2010
Highly Influential
9 Excerpts

Finite mixture models

  • G. J. McLachlan, D. Peel
  • Wiley New York,
  • 2000
Highly Influential
3 Excerpts

Similar Papers

Loading similar papers…