Quantitative bounds of convergence for geometrically ergodic Markov chain in the Wasserstein distance with application to the Metropolis Adjusted Langevin Algorithm.
Alain DurmusEric MoulinesPublished in: Stat. Comput. (2015)
Keyphrases
- markov chain
- monte carlo
- markov model
- worst case
- monte carlo simulation
- learning algorithm
- dynamic programming
- k means
- markov chain monte carlo
- transition matrix
- population size
- state space
- transition probabilities
- algo rithm
- markov process
- finite state
- steady state
- simulated annealing
- search space
- expectation maximization
- stationary distribution
- confidence intervals
- random walk
- stochastic process
- upper bound
- probabilistic model
- monte carlo method
- machine learning