Adaptive MCMC with Bayesian optimization

Journal of Machine Learning Research

Volumn 22, Issue , 2012, Pages 751-760

  Mahendran, Nimalan ^a   Wang, Ziyu ^a   Hamze, Firas ^a   De Freitas, Nando ^a  

^a D WAVE SYSTEMS INC   (Canada)

Author keywords

[No Author keywords available]

Indexed keywords

MARKOV PROCESSES;

ADAPTIVE MCMC; BAYESIAN OPTIMIZATION; EXPLORATION AND EXPLOITATION; NON-DIFFERENTIABLE OBJECTIVES; PROBABILISTIC GRAPHICAL MODELS; RANDOMIZED STRATEGY;

ARTIFICIAL INTELLIGENCE;

EID: 84954528329     PISSN: 15324435     EISSN: 15337928     Source Type: Journal    
DOI: None     Document Type: Conference Paper

References (37)

1. Ackley, David H., Hinton, Geoffrey E., and Sejnowski, Terrence J. A learning algorithm for Boltzmann machines. Cognitive Science, 9: 147-169, 1985.
2. Andrieu, Christophe and Moulines, Eric. On the ergodicity properties of some adaptive MCMC algorithms. The Annals of Applied Probability, 16 (3): 1462-1505, 2006.
3. Andrieu, Christophe and Robert, Christian. Controlled MCMC for optimal sampling. Technical Report 0125, Cahiers de Mathematiques du Ceremade, Universite Paris-Dauphine, 2001.
4. Andrieu, Christophe and Thoms, Johannes. A tutorial on adaptive MCMC. Statistics and Computing, 18 (4): 343-373, 2008.
5. Andrieu, Christophe, de Freitas, Nando, Doucet, Arnaud, and Jordan, Michael I. An Introduction to MCMC for Machine Learning. Machine Learning, 50 (1): 5-43, January 2003.
6. Atchade, Yves, Gersende Fort, Eric Moulines, and Priouret, Pierre. Adaptive Markov chain Monte Carlo: Theory and methods. Technical report, University of Michigan, 2009.
7. Bertsekas, Dimitri P. Projected Newton methods for optimization problems with simple constraints. SIAM J. on Control and Optimization, 20 (2): 221-246, 1982.
8. Brochu, Eric, Cora, Vlad M., and de Freitas, Nando. A tutorial on Bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning. Technical Report TR-2009-23, Department of Computer Science, University of British Columbia, November 2009.
9. Bull, Adam D. Convergence rates of efficient global optimization algorithms. Arxiv preprint arXiv: 1101.3501, 2011.
10. Diggle, P. J., Tawn, J. A., and Moyeed, R. A. Modelbased geostatistics. Journal of the Royal Statistical Society. Series C (Applied Statistics), 47 (3): 299-350, 1998.
11. Duane, Simon, Kennedy, A. D., Pendleton, Brian J., and Roweth, Duncan. Hybrid Monte Carlo. Physics letters B, 195 (2): 216-222, 1987.
12. Finkel, Daniel E. DIRECT Optimization Algorithm User Guide. 2003.
13. Gelman, Andrew, Roberts, Gareth O., and Gilks, Walter R. Efficient Metropolis jumping rules. In Bernado, J. M. et al. (eds.), Bayesian Statistics, volume 5, pp. 599. OUP, 1996.
14. Gramacy, Robert B., Lee, Herbert K. H., and Macready, William G. Parameter space exploration with Gaussian process trees. In International Conference on Machine Learning, pp. 45-52, 2004.
15. Haario, Heikki, Saksman, Eero, and Tamminen, Johanna. An adaptive Metropolis algorithm. Bernoulli, 7 (2): 223-242, 2001.
16. Hamze, Firas and de Freitas, Nando. Intracluster moves for constrained discrete-space MCMC. In Uncertainty in Artificial Intelligence, pp. 236-243, 2010.
17. Hamze, Firas, Wang, Ziyu, and de Freitas, Nando. Self-avoiding random dynamics on integer complex systems. Technical Report arXiv: 1111.5379v2, 2011.
18. Hoffman, Matt, Brochu, Eric, and de Freitas, Nando. Portfolio allocation for Bayesian optimization. In Uncertainty in Artificial Intelligence, pp. 327-336, 2011.
19. Kawasaki, Kyozi. Diffusion constants near the critical point for time-dependent Ising models. i. Phys. Rev., 145 (1): 224-230, 1966.
20. Lizotte, Daniel. Practical Bayesian Optimization. PhD thesis, University of Alberta, Edmonton, Alberta, Canada, 2008.
21. Lizotte, Daniel, Greiner, Russell, and Schuurmans, Dale. An experimental methodology for response surface optimization methods. Journal of Global Optimization, pp. 1-38, 2011.
22. May, Benedict C, Korda, Nathan, Lee, Anthony, and Leslie, David S. Optimistic Bayesian sampling in contextual bandit problems. 2011.
23. Neal, Radford M. MCMC using Hamiltonian dynamics. Handbook of Markov Chain Monte Carlo, 2010.
24. Osborne, Michael. Bayesian Gaussian Processes for Sequential Prediction, Optimisation and Quadrature. PhD thesis, University of Oxford, Oxford, UK, 2010.
25. Rasmussen, Carl E. and Williams, Christopher. Gaussian Processes for Machine Learning. MIT Press, 2006.
26. Rasmussen, Carl Edward. Gaussian processes to speed up hybrid Monte Carlo for expensive Bayesian integrals. Bayesian Statistics, 7: 651-659, 2003.
27. Robert, Christian P. and Casella, George. Monte Carlo Statistical Methods. Springer, 1st edition, 1998.
28. Roberts, Gareth O. and Rosenthal, Jeffrey S. Coupling and ergodicity of adaptive Markov chain Monte Carlo algorithms. Journal of applied probability, 44 (2): 458-475, 2007.
29. Roberts, Gareth O. and Rosenthal, Jeffrey S. Examples of adaptive MCMC. Journal of Computational and Graphical Statistics, 18 (2): 349-367, 2009.
30. Saksman, Eero and Vihola, Matti. On the ergodicity of the adaptive Metropolis algorithm on unbounded domains. Annals of Applied Probability, 20 (6): 2178-2203, 2010.
31. Santner, T J, Williams, B, and Notz, W. The Design and Analysis of Computer Experiments. Springer, 2003.
32. Schonlau, Matthias, Welch, William J., and Jones, Donald R. Global versus local search in constrained optimization of computer models. Lecture Notes- Monograph Series, 34: 11-25, 1998.
33. Srinivas, Niranjan, Krause, Andreas, Kakade, Sham M, and Seeger, Matthias. Gaussian process optimization in the bandit setting: No regret and experimental design. In Proc. International Conference on Machine Learning (ICML), 2010.
34. Vasquez, Emmanuel and Bect, Julien. On the convergence of the expected improvement algorithm. Technical Report arXiv: 0712.3744v2, arXiv.org, Feb 2008.
35. Vihola, Matti. Grapham: Graphical models with adaptive random walk Metropolis algorithms. Computational Statistics and Data Analysis, 54 (1): 49-54, 2010.
36. Wang, Ziyu and de Freitas, Nando. Predictive adaptation of hybrid Monte Carlo with Bayesian parametric bandits. In NIPS 2011 Deep Learning and Unsupervised Feature Learning Workshop, 2011.
37. Ye, Kenny Q. Orthogonal column Latin hypercubes and their application in computer experiments. Journal of the American Statistical Association, 93 (444): 1430-1439, 1998.