Sampling algorithms in statistical physics: a guide for statistics and machine learning

Abstract

We discuss several algorithms for sampling from unnormalized probability distributions in statistical physics, but using the language of statistics and machine learning. We provide a self-contained introduction to some key ideas and concepts of the field, before discussing three well-known problems: phase transitions in the Ising model, the melting transition on a two-dimensional plane and simulation of an all-atom model for liquid water. We review the classical Metropolis, Glauber and molecular dynamics sampling algorithms before discussing several more recent approaches, including cluster algorithms, novel variations of hybrid Monte Carlo and Langevin dynamics and piece-wise deterministic processes such as event chain Monte Carlo. We highlight cross-over with statistics and machine learning throughout and present some results on event chain Monte Carlo and sampling from the Ising model using tools from the statistics literature. We provide a simulation study on the Ising and XY models, with reproducible code freely available online, and following this we discuss several open areas for interaction between the disciplines that have not yet been explored and suggest avenues for doing so.

arXiv comment39 pages, 12 figures

References in corpus (48)

• An efficient, multiple range random walk algorithm to calculate the density of states
• The No-U-Turn Sampler: Adaptively Setting Path Lengths in Hamiltonian Monte Carlo
• Two-step melting in two dimensions: First-order liquid-hexatic transition
• 2D Melting: From Liquid-Hexatic Coexistence to Continuous Transitions
• A General Framework for the Parametrization of Hierarchical Models
• Hard-disk equation of state: First-order liquid-hexatic transition in two dimensions with three simulation methods
• A General Framework for Updating Belief Distributions
• Event-chain Monte Carlo algorithms for hard-sphere systems
• Computer simulations of the two-dimensional melting transition using hard disks
• Generalized event-chain Monte Carlo: Constructing rejection-free global-balance algorithms from infinitesimal steps
• The Zig-Zag Process and Super-Efficient Sampling for Bayesian Analysis of Big Data
• Rejection-free Monte-Carlo sampling for general potentials
• Irreversible Monte Carlo Algorithms for Efficient Sampling
• Joint Image Reconstruction and Segmentation Using the Potts Model
• Geometric integrators and the Hamiltonian Monte Carlo method
• Onsager's Wien Effect on a Lattice
• Principles of Bayesian Inference using General Divergence Criteria
• Piecewise Deterministic Markov Processes for Continuous-Time Monte Carlo
• Ergodicity of the zigzag process
• Proof of the Boltzmann-Sinai Ergodic Hypothesis for Typical Hard Disk Systems
• Discontinuous Hamiltonian Monte Carlo for discrete parameters and discontinuous likelihoods
• Event-chain Monte Carlo for classical continuous spin models
• Modified Hamiltonian Monte Carlo for Bayesian inference
• Monte Carlo Simulation of Dense Polymer Melts Using Event Chain Algorithms
• A comparison of learning rate selection methods in generalized Bayesian inference
• Cell-veto Monte Carlo algorithm for long-range systems
• Bayesian Nonparametric Ordination for the Analysis of Microbial Communities
• Extra Chance Generalized Hybrid Monte Carlo
• AC Wien effect in spin ice, manifest in non-linear non-equilibrium susceptibility
• All-atom computations with irreversible Markov chains
• Efficient Equilibration of Hard Spheres with Newtonian Event Chains
• Gibbs posterior concentration rates under sub-exponential type losses
• Importance sampling type estimators based on approximate marginal MCMC
• From quantum to thermal topological-sector fluctuations of strongly interacting bosons in a ring lattice
• Error Analysis of Modified Langevin Dynamics
• Parallelized event chain algorithm for dense hard sphere and polymer systems
• JeLLyFysh-Version1.0 -- a Python application for all-atom event-chain Monte Carlo
• Multi-stage splitting integrators for sampling with modified Hamiltonian Monte Carlo methods
• Irreversible Markov chains in spin models: Topological excitations
• Topological-sector fluctuations and ergodicity breaking at the Berezinskii-Kosterlitz-Thouless transition
• Langevin dynamics with general kinetic energies
• Accelerated Sampling on Discrete Spaces with Non-Reversible Markov Processes
• A general perspective on the Metropolis-Hastings kernel
• Hard-disk dipoles and non-reversible Markov chains
• Importance sampling correction versus standard averages of reversible MCMCs in terms of the asymptotic variance
• PDMP characterisation of event-chain Monte Carlo algorithms for particle systems
• Uniform minorization condition and convergence bounds for discretizations of kinetic Langevin dynamics
• Computational statistical physics and hypocoercivity

Cited by in corpus (2)

• Solution of the Metropolis dynamics on a complete graph with application to the Markov chain Mpemba effect
• Emergent electrostatics in planar XY spin models: the bridge connecting topological order with broken $U(1)$ symmetry