The DOI matches its Crossref record; 47 of the 47 references it cites were found in a registry or an index.
Optimal tuning of the hybrid Monte Carlo algorithm
Open accessAbstract
We investigate the properties of the hybrid Monte Carlo algorithm (HMC) in high dimensions. HMC develops a Markov chain reversible with respect to a given target distribution $\Pi$ using separable Hamiltonian dynamics with potential $-\log\Pi$. The additional momentum variables are chosen at random from the Boltzmann distribution, and the continuous-time Hamiltonian dynamics are then discretised using the leapfrog scheme. The induced bias is removed via a Metropolis–Hastings accept/reject rule. In the simplified scenario of independent, identically distributed components, we prove that, to obtain an $\mathcal{O}(1)$ acceptance probability as the dimension $d$ of the state space tends to $\infty$, the leapfrog step size $h$ should be scaled as $h=l\times d^{-1/4}$. Therefore, in high dimensions, HMC requires $\mathcal{O}(d^{1/4})$ steps to traverse the state space. We also identify analytically the asymptotically optimal acceptance probability, which turns out to be $0.651$ (to three decimal places). This value optimally balances the cost of generating a proposal, which decreases as $l$ increases (because fewer steps are required to reach the desired final integration time), against the cost related to the average number of proposals required to obtain acceptance, which increases as $l$ increases.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Equation of State Calculations by Fast Computing Machines
Metropolis, N., Rosenbluth, A. W., Rosenbluth, M. N., Teller, A. H., & Teller, E. (1953) · The Journal of Chemical Physics · doi:10.1063/1.1699114 · Cited by 37,192
Solving Ordinary Differential Equations II
Hairer, E., & Wanner, G. (1996) · Springer Series in Computational Mathematics · doi:10.1007/978-3-642-05221-7 · Cited by 4,342
Bayesian Learning for Neural Networks
Neal, R. M. (1996) · Lecture Notes in Statistics · doi:10.1007/978-1-4612-0745-0 · Cited by 4,276
Solving ordinary differential equations I. nonstiff problems
(1987) · Mathematics and Computers in Simulation · doi:10.1016/0378-4754(87)90083-8 · Cited by 4,077
Duane, S., Kennedy, A. D., Pendleton, B. J., & Roweth, D. (1987) · Physics Letters B · doi:10.1016/0370-2693(87)91197-x · Cited by 3,872
Geometric Numerical Integration
(2006) · Springer Series in Computational Mathematics · doi:10.1007/3-540-30666-8 · Cited by 3,118
Monte Carlo Strategies in Scientific Computing
Liu, J. S. (2004) · Springer Series in Statistics · doi:10.1007/978-0-387-76371-2 · Cited by 2,690
Martingale Limit Theory and its Application.
Loynes, R. M., Hall, P., & Heyde, C. C. (1984) · Journal of the Royal Statistical Society. Series A (General) · doi:10.2307/2981599 · Cited by 2,685
Martingale Limit Theory and its Application
(1980) · Elsevier eBooks · doi:10.1016/c2013-0-10818-5 · Cited by 1,912
Geometric Numerical Integration
Hairer, E., Wanner, G., & Lubich, C. (2002) · Springer Series in Computational Mathematics · doi:10.1007/978-3-662-05018-7 · Cited by 1,704
Equation of state calculations by fast computing machines
Metropolis, N., Rosenbluth, A. W., Rosenbluth, M. N., Teller, A. H., & Teller, E. (1953) · doi:10.2172/4390578 · Cited by 1,701
Weak convergence and optimal scaling of random walk Metropolis algorithms
Roberts, G. O., Gelman, A., & Gilks, W. R. (1997) · The Annals of Applied Probability · doi:10.1214/aoap/1034625254 · Cited by 1,693
Self-citationRiemann manifold langevin and hamiltonian monte carlo methods
Girolami, M., & Calderhead, B. (2011) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.1467-9868.2010.00765.x · Cited by 1,473
Simulating Hamiltonian Dynamics
Leimkuhler, B., & Reich, S. (2005) · Cambridge University Press eBooks · doi:10.1017/cbo9780511614118 · Cited by 1,130
Optimal scaling for various Metropolis-Hastings algorithms
Roberts, G. O., & Rosenthal, J. S. (2001) · Statistical Science · doi:10.1214/ss/1015346320 · Cited by 1,103
Self-citationProbabilistic Inference Using Markov Chain Monte Carlo Methods
Neal, R. M. (2011) · Cited by 1,040
Exponential Convergence of Langevin Distributions and Their Discrete Approximations
Roberts, G. O., & Tweedie, R. L. (1996) · Bernoulli · doi:10.2307/3318418 · Cited by 998
Self-citationHoover, W. G. (2014) · Cited by 682
Optimal Scaling of Discrete Approximations to Langevin Diffusions
Roberts, G. O., & Rosenthal, J. S. (1998) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/1467-9868.00123 · Cited by 632
Self-citationEfficient molecular dynamics and hybrid Monte Carlo algorithms for path integrals
Tuckerman, M. E., Berne, B. J., Martyna, G. J., & Klein, M. L. (1993) · The Journal of Chemical Physics · doi:10.1063/1.465188 · Cited by 539
Brownian dynamics as smart Monte Carlo simulation
Rossky, P. J., Doll, J. D., & Friedman, H. L. (1978) · The Journal of Chemical Physics · doi:10.1063/1.436415 · Cited by 509
Molecular dynamics, Langevin and hydrid Monte Carlo simulations in a multicanonical ensemble
Hansmann, U. H. E., Okamoto, Y., & Eisenmenger, F. (1996) · Chemical Physics Letters · doi:10.1016/0009-2614(96)00761-0 · Cited by 290
Analysis of a nonreversible Markov chain sampler
Diaconis, P., Holmes, S., & Neal, R. M. (2000) · The Annals of Applied Probability · doi:10.1214/aoap/1019487508 · Cited by 284
Hamiltonian evolution for the hybrid Monte Carlo algorithm
Sexton, J. C., & Weingarten, D. (1992) · Nuclear Physics B · doi:10.1016/0550-3213(92)90263-b · Cited by 256
On a novel Monte Carlo scheme for simulating water and aqueous solutions
Pangali, C., Rao, M., & Berne, B. J. (1978) · Chemical Physics Letters · doi:10.1016/0009-2614(78)84003-2 · Cited by 206
MCMC METHODS FOR DIFFUSION BRIDGES
BESKOS, A., ROBERTS, G., STUART, A., & VOSS, J. (2008) · Stochastics and Dynamics · doi:10.1142/s0219493708002378 · Cited by 166
Self-citationShadow hybrid Monte Carlo: an efficient propagator in phase space of macromolecules
Izaguirre, J. A., & Hampton, S. S. (2004) · Journal of Computational Physics · doi:10.1016/j.jcp.2004.04.016 · Cited by 134
Hybrid Monte Carlo on Hilbert spaces
Beskos, A., Pinski, F. J., Sanz-Serna, J. M., & Stuart, A. M. (2011) · Stochastic Processes and their Applications · doi:10.1016/j.spa.2011.06.003 · Cited by 120
Self-citationTheoretical and numerical comparison of some sampling methods for molecular dynamics
Eric Cancès, B., Legoll, F., & Stoltz, G. (2007) · ESAIM Mathematical Modelling and Numerical Analysis · doi:10.1051/m2an:2007014 · Cited by 116
Conformational Dynamics: Modelling, Theory, Algorithm, and Application to Biomolecules
Schütte, C. (1999) · Cited by 106
The acceptance probability in the hybrid Monte Carlo method
Sourendu Gupta, A., Irbäc, A., Karsch, F., et al. (1990) · Physics Letters B · doi:10.1016/0370-2693(90)91790-i · Cited by 103
Optimal acceptance rates for Metropolis algorithms: Moving beyond 0.234
Bédard, M. (2008) · Stochastic Processes and their Applications · doi:10.1016/j.spa.2007.12.005 · Cited by 99
Optimal scalings for local Metropolis–Hastings chains on nonproduct targets in high dimensions
Beskos, A., Roberts, G. O., & Stuart, A. M. (2009) · The Annals of Applied Probability · doi:10.1214/08-aap563 · Cited by 98
Self-citationDiffusion limits of the random walk Metropolis algorithm in high dimensions
Mattingly, J. C., Pillai, N. S., & Stuart, A. M. (2012) · The Annals of Applied Probability · doi:10.1214/10-aap754 · Cited by 94
Self-citationOptimal scaling and diffusion limits for the Langevin algorithm in high dimensions
Pillai, N. S., Stuart, A. M., & Thiéry, A. H. (2012) · The Annals of Applied Probability · doi:10.1214/11-aap828 · Cited by 86
Self-citationScaling Limits for the Transient Phase of Local Metropolis–Hastings Algorithms
Christensen, O. F., Roberts, G. O., & Rosenthal, J. S. (2005) · Journal of the Royal Statistical Society Series B (Statistical Methodology) · doi:10.1111/j.1467-9868.2005.00500.x · Cited by 86
Self-citationWeak convergence of Metropolis algorithms for non-i.i.d. target distributions
Bédard, M. (2007) · The Annals of Applied Probability · doi:10.1214/105051607000000096 · Cited by 84
Adaptively Scaling the Metropolis Algorithm Using Expected Squared Jumped DistancePreprint
Gelman, A., & Pasarica, C. (2007) · SSRN Electronic Journal · doi:10.2139/ssrn.1010403 · Cited by 80
Comparison of Stochastic Sampling Algorithms for Uncertainty Quantification
Mohamed, L., Christie, M., & Demyanov, V. (2009) · SPE Reservoir Simulation Conference · doi:10.2118/119139-ms · Cited by 54
Accelerated Monte Carlo for Optimal Estimation of Time Series
Alexander, F. J., Eyink, G. L., & Restrepo, J. M. (2005) · Journal of Statistical Physics · doi:10.1007/s10955-005-3770-1 · Cited by 50
A comparison of generalized hybrid Monte Carlo methods with and without momentum flip
Akhmatskaya, E. V., Bou-Rabee, N. M., & Reich, S. (2008) · Journal of Computational Physics · doi:10.1016/j.jcp.2008.12.014 · Cited by 50
Integration Schemes for Molecular Dynamics and Related Applications
Skeel, R. D. (1999) · Springer series in computational mathematics · doi:10.1007/978-3-662-03972-4_4 · Cited by 45
MCMC methods for sampling function space
Beskos, A., & Stuart, A. M. (2009) · doi:10.4171/056-1/16 · Cited by 41
Self-citationRiemannian Manifold Hamiltonian Monte CarloPreprint
Girolami, M., Calderhead, B., & Chin, S. (2009) · Cambridge University Engineering Department Publications Database · doi:10.48550/arxiv.0907.1100 · Cited by 33
Exploring Hybrid Monte Carlo in Bayesian Computation
Chen, L., Qin, Z. S., & Liu, J. S. (2000) · Cited by 19
Efficient Sampling Using Metropolis Algorithms: Applications of Optimal Scaling Results
Bédard, M. (2008) · Journal of Computational and Graphical Statistics · doi:10.1198/108571108x319970 · Cited by 16
Manifold Stochastic Dynamics for Bayesian Learning
Zlochin, M., & Yoram Baram, A. (2001) · Neural Computation · doi:10.1162/089976601753196021 · Cited by 10
Cited by
The geometric foundations of Hamiltonian Monte Carlo
Betancourt, M., Byrne, S., Livingstone, S., & Girolami, M. (2017) · Bernoulli · doi:10.3150/16-bej810 · Cited by 452
Mbalawata, I. S., Särkkä, S., & Haario, H. (2013) · Computational Statistics · doi:10.1007/s00180-012-0352-y · Cited by 77
Metadata
- Authors
- Beskos, A., Pillai, N., Roberts, G., Sanz-Serna, J.-M., & Stuart, A.
- Venue
- Bernoulli
- Published
- 2013-11-01
- Volume
- 19
- Issue
- 5A
- Pages
- 1501-1534
- ISSN
- 1350-7265 (ISSN-L)
- OpenAlex
- W1981514681
- Cited by
- 261
- References
- 47
- FWCI
- 18.06
- Type
- journal article
- Language
- en
- Open access
- bronze
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.