A collection on MCMC in Python

收集了一些python下mcmc的实现。

• Frequentism and Bayesianism IV: How to be a Bayesian in Python

  • http://jakevdp.github.io/blog/2014/06/14/frequentism-and-bayesianism-4-bayesian-in-python/

  • Comparison of three package: emcee, pymc and pystan.

• Comparison of sampling techniques for Bayesian parameter
  estimation

  • https://arxiv.org/pdf/1308.2675.pdf

  We find that nested sampling delivers high-fidelity estimates for posterior statistics at low computational cost, and should be adopted in favour of Metropolis-Hastings in many cases. Affine-invariant MCMC is competitive when computing clusters can be utilised for massive parallelisation. Affine-invariant MCMC and existing extensions to nested sampling naturally probe multi-modal and curving distributions.

• emcee

  • http://dan.iel.fm/emcee/current/

  • Ensemble Samplers with Affine Invariance, PDF

  • quick start

  • ipynb example

• pymc3

  • https://pymc-devs.github.io/pymc3/index.html

  • support NUTS, Metropolis, etc.

  • NUTS: an extension to Hamiltonian Monte Carlo (HMC).

• multinest

  • http://ccpforge.cse.rl.ac.uk/gf/project/multinest/

  • http://johannesbuchner.github.io/PyMultiNest/

  • paper

  • multimodal nested sampling algorithm

• Cross-Entropy

  • http://iew3.technion.ac.il/CE/index.php

  • wiki and reference therein.