Results 1  10
of
128
Monte Carlo Statistical Methods
, 1998
"... This paper is also the originator of the Markov Chain Monte Carlo methods developed in the following chapters. The potential of these two simultaneous innovations has been discovered much latter by statisticians (Hastings 1970; Geman and Geman 1984) than by of physicists (see also Kirkpatrick et al. ..."
Abstract

Cited by 1222 (25 self)
 Add to MetaCart
This paper is also the originator of the Markov Chain Monte Carlo methods developed in the following chapters. The potential of these two simultaneous innovations has been discovered much latter by statisticians (Hastings 1970; Geman and Geman 1984) than by of physicists (see also Kirkpatrick et al. 1983). 5.5.5 ] PROBLEMS 211
ActorCritic Algorithms
 SIAM JOURNAL ON CONTROL AND OPTIMIZATION
, 2001
"... In this paper, we propose and analyze a class of actorcritic algorithms. These are twotimescale algorithms in which the critic uses temporal difference (TD) learning with a linearly parameterized approximation architecture, and the actor is updated in an approximate gradient direction based on in ..."
Abstract

Cited by 220 (1 self)
 Add to MetaCart
In this paper, we propose and analyze a class of actorcritic algorithms. These are twotimescale algorithms in which the critic uses temporal difference (TD) learning with a linearly parameterized approximation architecture, and the actor is updated in an approximate gradient direction based on information provided by the critic. We show that the features for the critic should ideally span a subspace prescribed by the choice of parameterization of the actor. We study actorcritic algorithms for Markov decision processes with general state and action spaces. We state and prove two results regarding their convergence.
General state space Markov chains and MCMC algorithm
 PROBABILITY SURVEYS
, 2004
"... This paper surveys various results about Markov chains on general (noncountable) state spaces. It begins with an introduction to Markov chain Monte Carlo (MCMC) algorithms, which provide the motivation and context for the theory which follows. Then, sufficient conditions for geometric and uniform e ..."
Abstract

Cited by 139 (35 self)
 Add to MetaCart
This paper surveys various results about Markov chains on general (noncountable) state spaces. It begins with an introduction to Markov chain Monte Carlo (MCMC) algorithms, which provide the motivation and context for the theory which follows. Then, sufficient conditions for geometric and uniform ergodicity are presented, along with quantitative bounds on the rate of convergence to stationarity. Many of these results are proved using direct coupling constructions based on minorisation and drift conditions. Necessary and sufficient conditions for Central Limit Theorems (CLTs) are also presented, in some cases proved via the Poisson Equation or direct regeneration constructions. Finally, optimal scaling and weak convergence results for MetropolisHastings algorithms are discussed. None of the results presented is new, though many of the proofs are. We also describe some Open Problems.
Shuffling cards and stopping times
 In Proceedings of the 43rd IEEE Conference on Decision and Control
, 1986
"... 1. Introduction. How many times must a deck of cards be shuffled until it is close to random? There is an elementary technique which often yields sharp estimates in such problems. The method is best understood through a simple example. EXAMPLE1. Top in at random shuffle. Consider the following metho ..."
Abstract

Cited by 115 (14 self)
 Add to MetaCart
1. Introduction. How many times must a deck of cards be shuffled until it is close to random? There is an elementary technique which often yields sharp estimates in such problems. The method is best understood through a simple example. EXAMPLE1. Top in at random shuffle. Consider the following method of mixing a deck of cards: the top card is removed and inserted into the deck at a random position. This procedure is
Regeneration in Markov Chain Samplers
, 1994
"... Markov chain sampling has received considerable attention in the recent literature, in particular in the context of Bayesian computation and maximum likelihood estimation. This paper discusses the use of Markov chain splitting, originally developed as a tool for the theoretical analysis of general s ..."
Abstract

Cited by 103 (5 self)
 Add to MetaCart
Markov chain sampling has received considerable attention in the recent literature, in particular in the context of Bayesian computation and maximum likelihood estimation. This paper discusses the use of Markov chain splitting, originally developed as a tool for the theoretical analysis of general state space Markov chains, to introduce regeneration times into Markov chain samplers. This allows the use of regenerative methods for analyzing the output of these samplers, and can also provide a useful diagnostic of the performance of the samplers. The general approach is applied to several different samplers and is illustrated in a number of examples. 1 Introduction In Markov chain Monte Carlo, a distribution ß is examined by obtaining sample paths from a Markov chain constructed to have equilibrium distribution ß. This approach was introduced by Metropolis et al. (1953) and has recently received considerable attention as a method for examining posterior distributions in Bayesian infer...
Honest Exploration of Intractable Probability Distributions Via Markov Chain Monte Carlo
 STATISTICAL SCIENCE
, 2001
"... Two important questions that must be answered whenever a Markov chain Monte Carlo (MCMC) algorithm is used are (Q1) What is an appropriate burnin? and (Q2) How long should the sampling continue after burnin? Developing rigorous answers to these questions presently requires a detailed study of the ..."
Abstract

Cited by 89 (29 self)
 Add to MetaCart
Two important questions that must be answered whenever a Markov chain Monte Carlo (MCMC) algorithm is used are (Q1) What is an appropriate burnin? and (Q2) How long should the sampling continue after burnin? Developing rigorous answers to these questions presently requires a detailed study of the convergence properties of the underlying Markov chain. Consequently, in most practical applications of MCMC, exact answers to (Q1) and (Q2) are not sought. The goal of this paper is to demystify the analysis that leads to honest answers to (Q1) and (Q2). The authors hope that this article will serve as a bridge between those developing Markov chain theory and practitioners using MCMC to solve practical problems. The ability to formally address (Q1) and (Q2) comes from establishing a drift condition and an associated minorization condition, which together imply that the underlying Markov chain is geometrically ergodic. In this paper, we explain exactly what drift and minorization are as well as how and why these conditions can be used to form rigorous answers to (Q1) and (Q2). The basic ideas are as follows. The results of Rosenthal (1995) and Roberts and Tweedie (1999) allow one to use drift and minorization conditions to construct a formula giving an analytic upper bound on the distance to stationarity. A rigorous answer to (Q1) can be calculated using this formula. The desired characteristics of the target distribution are typically estimated using ergodic averages. Geometric ergodicity of the underlying Markov chain implies that there are central limit theorems available for ergodic averages (Chan and Geyer 1994). The regenerative simulation technique (Mykland, Tierney and Yu 1995, Robert 1995) can be used to get a consistent estimate of the variance of the asymptotic nor...
Convergence rates of Markov chains
, 1995
"... this paper, we attempt to describe various mathematical techniques which have been used to bound such rates of convergence. In particular, we describe eigenvalue analysis, random walks on groups, coupling, and minorization conditions. Connections are made to modern areas of research wherever possibl ..."
Abstract

Cited by 74 (4 self)
 Add to MetaCart
this paper, we attempt to describe various mathematical techniques which have been used to bound such rates of convergence. In particular, we describe eigenvalue analysis, random walks on groups, coupling, and minorization conditions. Connections are made to modern areas of research wherever possible. Elements of linear algebra, probability theory, group theory, and measure theory are used, but efforts are made to keep the presentation elementary and accessible. Acknowledgements. I thank Eric Belsley for comments and corrections, and thank Persi Diaconis for introducing me to this subject and teaching me so much. 1. Introduction and motivation.
Likelihood Ratio Gradient Estimation For Stochastic Recursions
 Communications of the ACM
, 1995
"... . In this paper, we develop mathematical machinery for verifying that a broad class of general state space Markov chains reacts smoothly to certain types of perturbations in the underlying transition structure. Our main result provides conditions under which the stationary probability measure of an ..."
Abstract

Cited by 64 (7 self)
 Add to MetaCart
. In this paper, we develop mathematical machinery for verifying that a broad class of general state space Markov chains reacts smoothly to certain types of perturbations in the underlying transition structure. Our main result provides conditions under which the stationary probability measure of an ergodic Harris recurrent Markov chain is differentiable in a certain strong sense. The approach is based on likelihood ratio "changeofmeasure" arguments, and leads directly to a "likelihood ratio gradient estimator" that can be computed numerically. Keywords: Harris recurrent Markov chain, likelihood ratio, gradient estimation, regeneration. 1 The research of this author was supported by the U. S. Army Research Office under Contract No. DAAL0391G 0101 and by the National Science Foundation under Contract No. DDM9101580. 2 This author's research was supported by NSERCCanada grant No. OGP0110050 and FCARQu'ebec grant No. 93ER1654. 1. Introduction In this paper, we will study the cl...
Stochastically recursive sequences and their generalizations
 Siberian Adv. Math
, 1992
"... The paper deals with the stochastically recursive sequences { X ( n) } defined as the solutions of equations X ( n + 1) = f ( X ( n) , ξn) (where ξn is a given random sequence), and with random sequences of a more general nature, named recursive chains. For those the theorems of existence, ergodici ..."
Abstract

Cited by 46 (12 self)
 Add to MetaCart
(Show Context)
The paper deals with the stochastically recursive sequences { X ( n) } defined as the solutions of equations X ( n + 1) = f ( X ( n) , ξn) (where ξn is a given random sequence), and with random sequences of a more general nature, named recursive chains. For those the theorems of existence, ergodicity, stability are established, the stationary majorants are constructed. Continuoustime processes associated with ones studied here are considered as well. Key words and phrases: stochastically recursive sequence; recursive chain; generalized Markov chain; renovating event; couplingconvergence; ergodicity; stability; rate of convergence; stationary majorants; boundedness in probability; processes admitting embedded stochastically recursive sequences. CHAPTER 1.