Hamiltonian Monte Carlo without detailed balance

31st International Conference on Machine Learning, ICML 2014

Volumn 2, Issue , 2014, Pages 1081-1088

  Sohl Dickstein, Jascha ^a,b   Mudigonda, Mayur ^c   Deweese, Michael R ^c  

^a STANFORD UNIVERSITY   (United States)

^b Khan Academy   (United States)

^c UNIVERSITY OF CALIFORNIA   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ARTIFICIAL INTELLIGENCE; HAMILTONIANS; LEARNING SYSTEMS; MARKOV PROCESSES;

CHAIN TRANSITIONS; DETAILED BALANCE; FIXED POINT EQUATION; MIXING TIME; RANDOM WALK; SOURCE CODES; TEST PROBLEM;

MONTE CARLO METHODS;

EID: 84919914124     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (21)

1. Beskos, A and Pinski, FJ. Hybrid monte carlo on hilbert spaces. Stochastic Processes and their Applications, 2011.
2. Cadieu, CF and Koepsell, K. Phase coupling estimation from multivariate phase statistics. Neural computation, 2010.
3. Culpepper, Benjamin J, Sohl-Dickstein, Jascha, and shausen, Bruno A. Building a better probabilistic model of images by factorization. International Conference on Computer Vision, 2011.
4. Duane, S, Kennedy, AD, Pendleton, BJ, and Roweth, D. Hybrid monte carlo. Physics letters B, 1987.
5. Girolami, Mark, Calderhead, Ben, and Chin, Siu A. Riemann manifold Langevin and Hamiltonian Monte Carlo methods. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 73(2): 123-214, March 2011. ISSN 13697412. doi: 10.1111/j.1467-9868.2010. 00765.
6. Hairer, E, Lubich, C, and Wanner, G. Geometric numerical integration illustrated by the Stormer-Verlet method. Acta Numerica, 2003.
7. Hastings, W. Monte Carlo sampling methods using Markov chains and their applications. Biometrika, January 1970.
8. Hoffman, MD and Gelman, A. The No-U-Turn Sampler: Adaptively Setting Path Lengths in Hamiltonian Monte Carlo. Arxiv preprint arXiv: 1 111.4246, pp. 1-30, 2011.
9. Horowitz, AM. A generalized guided Monte Carlo algorithm. Physics Letters B, 1991.
10. Izaguirre, JA and Hampton, SS. Shadow hybrid Monte Carlo: An efficient propagator in phase space of macro- molecules. Journal of Computational Physics, 2004.
11. Kennedy, AD and Pendleton, B. Acceptances and autocorrelations in hybrid Monte Carlo. Nuclear Physics B- Proceedings Supplements, 1991.
12. MacKay, DJC. Information theory, inference and learning algorithms. 2003.
13. Neal, Radford M. MCMC using Hamiltonian dynamics. Handbook of Markov Chain Monte Carlo, January 2010.
14. Neal, RM. Probabilistic inference using Markov chain Monte Carlo methods. Technical Report CRG-TR-93-1, Dept. of Computer Science, University of Toronto, 1993.
15. Neal, RM. An improved acceptance procedure for the hybrid Monte Carlo algorithm. Journal of Computational Physics, 1994.
16. Schiitte, C and Fischer, A. A direct approach to conformational dynamics based on hybrid Monte Carlo. Journal of Computational Physics, 1999.
17. Shahbaba, B, Lan, S, Johnson, WO, and Neal, RM. Split hamiltonian monte carlo. Statistics and Computing, 2011.
18. Sohl-Dickstein, Jascha. Hamiltonian Monte Carlo with Reduced Momentum Flips. arXiv: 1205.1939vl, May 2012.
19. Sohl-Dickstein, Jascha and Culpepper, Benjamin J. Hamiltonian Annealed Importance Sampling for partition function estimation. arXiv:1205.1925vl, May 2012.
20. Wang, Z, Mohamed, S, and Nando, D. Adaptive Hamiltonian and Riemann Manifold Monte Carlo. Proceedings of the 30th International Conference on Machine Learning (ICML-13), 2013.
21. Zhang, Y and Sutton, C. Quasi-Newton Markov chain Monte Carlo. 2011.