Stability of adversarial Markov chains, with an application to adaptive MCMC algorithms

  title={Stability of adversarial Markov chains, with an application to adaptive MCMC algorithms},
  author={Radu V. Craiu and Lawrence Gray and K. Latuszynski and N. Madras and G. Roberts and J. Rosenthal},
  journal={Annals of Applied Probability},
  • Radu V. Craiu, Lawrence Gray, +3 authors J. Rosenthal
  • Published 2015
  • Mathematics
  • Annals of Applied Probability
  • We consider whether ergodic Markov chains with bounded step size remain bounded in probability when their transitions are modied by an adversary on a bounded subset. We provide counterexamples to show that the answer is no in general, and prove theorems to show that the answer is yes under various additional assumptions. We then use our results to prove convergence of various adaptive Markov chain Monte Carlo algorithms. 
    11 Citations

    Figures from this paper

    Air Markov Chain Monte Carlo
    • 2
    • PDF
    Convergence and Efficiency of Adaptive MCMC
    • 1
    • Highly Influenced
    • PDF
    Adaptive Incremental Mixture Markov Chain Monte Carlo
    • F. Maire, N. Friel, A. Mira, A. Raftery
    • Mathematics, Medicine
    • Journal of computational and graphical statistics : a joint publication of American Statistical Association, Institute of Mathematical Statistics, Interface Foundation of North America
    • 2019
    • 3
    • PDF
    Adaptive Schemes for Piecewise Deterministic Monte Carlo Algorithms
    • PDF
    A Framework for Adaptive MCMC Targeting Multimodal Distributions
    • 7
    • PDF
    MCMC adaptatifs à essais multiples
    Adaptive Component-Wise Multiple-Try Metropolis Sampling
    • 4
    • PDF


    On the containment condition for adaptive Markov chain Monte Carlo algorithms
    • 62
    • PDF
    Limit theorems for some adaptive MCMC algorithms with subgeometric kernels
    • 58
    • PDF
    The Containment Condition and Adapfail Algorithms
    • 9
    • PDF
    Adversarial queuing theory
    • 247
    • PDF