Stochastic gradient Hamiltonian Monte Carlo

31st International Conference on Machine Learning, ICML 2014

Volumn 5, Issue , 2014, Pages 3663-3676

  Chen, Tianqi ^a   Fox, Emily B ^a   Guestrin, Carlos ^a  

^a UNIVERSITY OF WASHINGTON   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ARTIFICIAL INTELLIGENCE; BAYESIAN NETWORKS; COMPUTATION THEORY; DYNAMICAL SYSTEMS; HAMILTONIANS; LEARNING SYSTEMS; PROBABILITY; STOCHASTIC SYSTEMS;

BAYESIAN MATRIX FACTORIZATIONS; CLASSIFICATION TASKS; GRADIENT COMPUTATION; HAMILTONIAN DYNAMICAL SYSTEMS; INVARIANT DISTRIBUTION; METROPOLIS-HASTINGS; STOCHASTIC APPROXIMATIONS; STOCHASTIC GRADIENT;

MONTE CARLO METHODS;

EID: 84919787787     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (22)

1. Ahn, S., Korattikara, A., and Welling, M. Bayesian posterior sampling via stochastic gradient Fisher scoring. In Proceedings of the 29th International Conference on Machine Learning (ICML'12), pp. 1591-1598, July 2012.
2. Bardenet, R., Doucet, A., and Holmes, C. Towards scaling up Markov chain Monte Carlo: An adaptive subsampling approach. In Proceedings of the 30th International Conference on Machine Learning (ICML'14), volume 32, p-p. 405-413, February 2014.
3. Duane, S., Kennedy, A.D., Pendleton, B.J., and Roweth, D. Hybrid Monte Carlo. Physics Letters B, 195(2):216-222, 1987.
4. Girolami, M. and Calderhead, B. Riemann manifold Langevin and Hamiltonian Monte Carlo methods. Journal of the Royal Statistical Society Series B, 73(2): 123 - 214, 03 2011.
5. Hoffman, M.D. and Gelman, A. The No-U-Turn sampler: Adaptively setting path lengths in Hamiltonian Monte Carlo. arXiv, 1111.4246, 2011.
6. Hoffman, M.D., Blei, D. M., Wang, C, and Paisley, J. Stochastic variational inference. Journal of Maching Learning Research, 14(1): 1303-1347, May 2013.
7. Horowitz, A.M. A generalized guided Monte Carlo algorithm. Physics Letters B, 268(2):247-252, 1991.
8. Korattikara, A., Chen, Y., and Welling, M. Austerity in MCMC land: Cutting the Metropolis-Hastings budget. In Proceedings of the 30th International Conference on Machine Learning (ICML'14), volume 32, pp. 181-189, February 2014.
9. Levin, D.A., Peres, Y., and Wilmer, E.L. Markov Chain-s and Mixing Times. American Mathematical Society, 2008.
10. Neal, R.M. Bayesian learning via stochastic dynamics. In Advances in Neural Information Processing Systems 5 (NIPS'93), pp. 475-482, 1993.
11. Neal, R.M. MCMC using Hamiltonian dynamics. Handbook of Markov Chain Monte Carlo, 54:113-162, 2010.
12. Nemirovski, A., Juditsky, A., Lan, G., and Shapiro, A. Robust stochastic approximation approach to stochastic programming. SIAM Journal on Optimization, 19(4): 1574-1609, January 2009.
13. Patterson, S. and Teh, Y.W Stochastic gradient Rieman-nian Langevin dynamics on the probability simplex. In Advances in Neural Information Processing Systems 26 (NIPS'13), pp. 3102-3110. 2013.
14. Robbins, H. and Monro, S. A stochastic approximation method. The Annals of Mathematical Statistics, 22(3): 400-407, 09 1951.
15. Salakhutdinov, R. and Mnih, A. Bayesian probabilistic matrix factorization using Markov chain Monte Carlo. In Proceedings of the 25th International Conference on Machine Learning (ICML'08), pp. 880-887, 2008a.
16. Salakhutdinov, R. and Mnih, A. Probabilistic matrix factorization. In Advances in Neural Information Processing Systems 20 (NIPS'08), pp. 1257-1264, 2008b.
17. Shi, J., Chen, T., Yuan, R., Yuan, B., and Ao, P. Relation of a new interpretation of stochastic differential equations to Ito process. Journal of Statistical Physics, 148(3): 579-590, 2012.
18. Sutskever, I., Martens, J., Dahl, G. E., and Hinton, G. E. On the importance of initialization and momentum in deep learning. In Proceedings of the 30th International Conference on Machine Learning (ICML'13), volume 28, p-p. 1139-1147, May 2013.
19. Wang, M.C. and Uhlenbeck, G.E. On the Theory of the Brownian Motion II. Reviews of Modern Physics, 17(2-3):323, 1945.
20. Wang, Z., Mohamed, S., and Nando, D. Adaptive Hamiltonian and Riemann manifold Monte Carlo. In Proceedings of the 30th International Conference on Machine Learning (ICML'13), volume 28, pp. 1462-1470, May 2013.
21. Welling, M. and Teh, Y.W. Bayesian learning via stochastic gradient Langevin dynamics. In Proceedings of the 28th International Conference on Machine Learning (ICM-L'11), pp. 681-688, June 2011.
22. Yin, L. and Ao, P. Existence and construction of dynamical potential in nonequilibrium processes without detailed balance. Journal of Physics A: Mathematical and General, 39(27):8593, 2006.