Understanding the Hastings Algorithm

  title={Understanding the Hastings Algorithm},
  author={David D. L. Minh and Do Le Paul Minh},
  journal={Communications in Statistics - Simulation and Computation},
  pages={332 - 349}
  • David D. L. Minh, Do Le Paul Minh
  • Published 2015
  • Computer Science, Mathematics
  • Communications in Statistics - Simulation and Computation
  • The Hastings algorithm is a key tool in computational science. While mathematically justified by detailed balance, it can be conceptually difficult to grasp. Here, we present two complementary and intuitive ways to derive and understand the algorithm. In our framework, it is straightforward to see that the celebrated Metropolis–Hastings algorithm has the highest acceptance probability of all Hastings algorithms. 

    Topics from this paper.

    Learning an efficient constructive sampler for graphs
    • 3
    Bayesian analysis of isothermal titration calorimetry for binding thermodynamics
    • 5
    Regenerative Markov Chain Importance Sampling
    • 2


    Publications referenced by this paper.
    Understanding the Metropolis-Hastings Algorithm
    • 3,495
    • PDF
    Equation of state calculations by fast computing machines
    • 29,454
    • PDF
    Markov Chains for Exploring Posterior Distributions
    • 3,339
    • PDF
    Monte Carlo Strategies in Scientific Computing
    • 1,198
    • PDF
    Monte Carlo strategies in scientific computing
    • 2,163
    Guest Editors Introduction to the top 10 algorithms
    • 245
    Optimum Monte-Carlo sampling using Markov chains
    • 475
    • PDF
    A geometric interpretation of the Metropolis-Hastings algorithm
    • 62
    • PDF
    Monte Carlo Strategies
    • 206