The Convergence of Markov Chain Monte Carlo Methods: From the Metropolis Method to Hamiltonian Monte Carlo

  title={The Convergence of Markov Chain Monte Carlo Methods: From the Metropolis Method to Hamiltonian Monte Carlo},
  author={Michael Betancourt},
  journal={Annalen der Physik},
From its inception in the 1950s to the modern frontiers of applied statistics, Markov chain Monte Carlo has been one of the most ubiquitous and successful methods in statistical computing. The development of the method in that time has been fueled by not only increasingly difficult problems but also novel techniques adopted from physics. Here, the history of Markov chain Monte Carlo is reviewed from its inception with the Metropolis method to the contemporary state‐of‐the‐art in Hamiltonian… 
Precision Annealing Monte Carlo Methods for Statistical Data Assimilation: Metropolis-Hastings Procedures
The idea of precision annealing (PA) is extended to Monte Carlo calculations of conditional expected values using Metropolis-Hastings methods and the Laplace method is used to identify the maxima of the conditional probability distribution.
Mixing rates for Hamiltonian Monte Carlo algorithms in finite and infinite dimensions
We establish the geometric ergodicity of the preconditioned Hamiltonian Monte Carlo (HMC) algorithm defined on an infinite-dimensional Hilbert space, as developed in [Beskos et al., Stochastic
Precision annealing Monte Carlo methods for statistical data assimilation and machine learning
This paper develops a systematic formulation based on Monte Carlo sampling to achieve information transfer to a nonlinear dynamical model with chaotic solutions widely used in geophysics.
Reversible Jump Probabilistic Programming
This paper presents a method for automatically deriving a Reversible Jump Markov chain Monte Carlo sampler from probabilistic programs that specify the target and proposal distributions, which relies on the interaction of several different components, including automatic differentiation, transformation inversion, and optimised code generation.
Adapting Hybrid Monte Carlo methods for solving complex problems in life and materials sciences
It is shown that equipping the Hybrid Monte Carlo algorithm with extra features makes it even a “smarter” sampler and, no doubts, a strong competitor to the wellestablished molecular simulation techniques such as molecular dynamics and Monte Carlo.
Hamiltonian Monte Carlo on Symmetric and Homogeneous Spaces via Symplectic Reduction
The Hamiltonian Monte Carlo method generates samples by introducing a mechanical system that explores the target density. For distributions on manifolds it is not always simple to perform the
Fast and Credible Likelihood-Free Cosmology with Truncated Marginal Neural Ratio Estimation
This paper shows that tmnre can achieve converged posteriors using orders of magnitude fewer simulator calls than conventional Markov Chain Monte Carlo methods, and promises to become a powerful tool for cosmological data analysis, particularly in the context of extended cosmologies.
On the accept-reject mechanism for Metropolis-Hastings algorithms
This work develops a powerful and versatile framework for determining acceptance ratios in Metropolis-Hastings type Markov kernels widely used in statistical sampling problems. Our approach allows us
Sensitivity of non-conditional climatic variables to climate-change deep uncertainty using Markov Chain Monte Carlo simulation
There is substantial evidence suggesting climate change is having an adverse impact on the world’s water resources. One must remember, however, that climate change is beset by uncertainty. It is
Assessing the Accuracy of Machine Learning Thermodynamic Perturbation Theory: Density Functional Theory and Beyond.
Machine learning thermodynamic perturbation theory (MLPT) is a promising approach to compute finite temperature properties when the goal is to compare several different levels of ab initio theory


A Short History of Markov Chain Monte Carlo: Subjective Recollections from Incomplete Data
The history and development of Markov chain Monte Carlo (MCMC) from its early inception in the late 1940's through its use today and how the development of this methodology has changed the way the authors think about problems is traced.
Monte Carlo Sampling Methods Using Markov Chains and Their Applications
SUMMARY A generalization of the sampling method introduced by Metropolis et al. (1953) is presented along with an exposition of the relevant theory, techniques of application and methods and
Probabilistic Inference Using Markov Chain Monte Carlo Methods
The role of probabilistic inference in artificial intelligence is outlined, the theory of Markov chains is presented, and various Markov chain Monte Carlo algorithms are described, along with a number of supporting techniques.
MCMC Using Hamiltonian Dynamics
Hamiltonian dynamics can be used to produce distant proposals for the Metropolis algorithm, thereby avoiding the slow exploration of the state space that results from the diffusive behaviour of
Marshall Rosenbluth and the Metropolis algorithma)
The algorithm described in this publication, known as the Metropolis algorithm, is described, reconstructs the historical context in which it was developed, and summarizes Marshall Rosenbluth's recollections.
Brownian dynamics as smart Monte Carlo simulation
A new Monte Carlo simulation procedure is developed which is expected to produce more rapid convergence than the standard Metropolis method. The trial particle moves are chosen in accord with a
Marshall Rosenbluth and the Metropolis algorithm a ...
The algorithm described in this publication subsequently became known as the Metropolis algorithm, undoubtedly the most famous and most widely used Monte Carlo algorithm ever published and the historical context in which it was developed is reconstructed.
Weak convergence and optimal scaling of random walk Metropolis algorithms
This paper considers the problem of scaling the proposal distribution of a multidimensional random walk Metropolis algorithm in order to maximize the efficiency of the algorithm. The main result is a
The Geometric Foundations of Hamiltonian Monte Carlo
The formal foundations of the algorithm are developed through the construction of measures on smooth manifolds, and how the theory naturally identifies efficient implementations and motivates promising generalizations are demonstrated.