Gradient-based MCMC samplers for dynamic causal modelling

NeuroImage

Volumn 125, Issue , 2016, Pages 1107-1118

  Sengupta, Biswa ^a   Friston, Karl J ^a   Penny, Will D ^a  

^a UNIVERSITY COLLEGE LONDON   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

ACCURACY; ALGORITHM; ARTICLE; CALCULATION; GEOMETRY; MARKOV CHAIN; MATHEMATICAL ANALYSIS; MATHEMATICAL MODEL; MONTE CARLO METHOD; NEURAL MASS MODEL; PRIORITY JOURNAL; SCORING SYSTEM; SIMULATION; BAYES THEOREM; COMPARATIVE STUDY; COMPUTER ASSISTED DIAGNOSIS; HUMAN; NEUROIMAGING; PROCEDURES; THEORETICAL MODEL;

ALGORITHMS; BAYES THEOREM; HUMANS; IMAGE INTERPRETATION, COMPUTER-ASSISTED; MARKOV CHAINS; MODELS, THEORETICAL; MONTE CARLO METHOD; NEUROIMAGING;

EID: 84940870400     PISSN: 10538119     EISSN: 10959572     Source Type: Journal    
DOI: 10.1016/j.neuroimage.2015.07.043     Document Type: Article

References (49)

1. Amari, S., Douglas, S.C., Why natural gradient?. Proceedings of the IEEE International Conference on Acoustics, Speech and, Signal Processing, vol. 2, 1998, 1213–1216 (May).
2. Beal, M.J., Variational Algorithms for Approximate Bayesian Inference. (PhD thesis), 2003, University College London.
3. Beskos, Alexandros, Pillai, Natesh, Roberts, Gareth, Sanz-Serna, Jesus-Maria, Stuart, Andrew, Optimal tuning of the hybrid Monte Carlo algorithm. Bernoulli 19:5A (2013), 1501–1534.
4. Betancourt, Michael, Stein, Leo C., The geometry of Hamiltonian Monte Carlo. 2011 (arXiv:1112.4118).
5. Betancourt, Michael, Byrne, Simon, Girolami, Mark, Optimizing the integrator step size for Hamiltonian Monte Carlo. 2015 (arXiv:1411.6669).
6. Betancourt, Michael, Byrne, Simon, Livingstone, Sam, Girolami, Mark, The geometric foundations of Hamiltonian Monte Carlo. Stat. Sci., 2015 (under review).
7. Bischof, Christian H., Martin Bücker, H., Lang, Bruno, Rasch, A., Vehreschild, Andre, Combining source transformation and operator overloading techniques to compute derivatives for MATLAB programs. Proceedings of the Second IEEE International Workshop on Source Code Analysis and Manipulation, 2002, 65–72.
8. Byrne, Simon, Girolami, Mark, Geodesic Monte Carlo on embedded manifolds. Scand. J. Stat. 40:4 (2013), 825–845.
9. Chumbley, Justin R., Friston, Karl J., Fearn, Tom, Kiebel, Stefan J., A Metropolis–Hastings algorithm for dynamic causal models. NeuroImage 38:3 (2007), 478–487.
10. Cormen, Thomas H., Stein, Clifford, Rivest, Ronald L., Leiserson, Charles E., Introduction to Algorithms. 2nd edition, 2001, McGraw-Hill Higher Education 0070131511.
11. Cowles, M.K., Carlin, B.P., Markov Chain Monte Carlo convergence diagnostics: A comparative review. J. Am. Stat. Assoc. 91:434 (1996), 883–904.
12. David, Olivier, Kilner, James M., Friston, Karl J., Mechanisms of evoked and induced responses in MEG/EEG. NeuroImage 31:4 (2006), 1580–1591.
13. Duane, S., Kennedy, A.D., Pendleton, B.J., Roweth, D., Hybrid Monte Carlo. Phys. Lett. B 195 (1987), 216–222.
14. Fiser, József, Berkes, Pietro, Orbán, Gergo, Lengyel, Máté, Statistically optimal perception and learning: from behavior to neural representations. Trends Cogn. Sci. 14:3 (2010), 119–130 (Mar).
15. Friston, K., Mattout, J., Trujillo-Barreto, N., Ashburner, J., Penny, W., Variational free energy and the Laplace approximation. NeuroImage 34 (2007), 220–234.
16. Friston, K.J., Harrison, L., Penny, W., Dynamic causal modelling. NeuroImage 19:4 (2003), 1273–1302.
17. Gelman, Andrew, Rubin, Donald B., Inference from iterative simulation using multiple sequences. Stat. Sci. 7:4 (1992), 457–472.
18. Geweke, J., Evaluating the accuracy of sampling-based approaches to calculating posterior moments. Bernardo, J.M., Berger, J., Dawid, A.P., Smith, J.F.M., (eds.) Bayesian Statistics 4, 1992, Oxford University Press, Oxford, 169–193.
19. Geyer, Charles J., Practical Markov Chain Monte Carlo. Stat. Sci. 08834237, 7(4), 1992, 473–483.
20. Girolami, Mark, Calderhead, Ben, Riemann manifold Langevin and Hamiltonian Monte Carlo methods. J. R. Stat. Soc. Ser. B 73:2 (2011), 123–214 (03).
21. Golub, Gene H., Van Loan, Charles F., Matrix Computations. 3rd ed., 2012, Johns Hopkins University Press, Baltimore, MD, USA.
22. Haario, H., Saksman, E., Tamminen, J., An adaptive Metropolis algorithm. Bernoulli 7:2 (2001), 223–242.
23. Hennequin, G., Aitchison, L., Lengyel, M., Fast sampling-based inference in balanced neuronal networks. Advances in Neural Information Processing Systems, 27, 2014.
24. Hindmarsh, A., Serban, R., User Documentation for CVODES, and ODE Solver with Sensitivity Analysis Capabilities. Technical Report, 2002, Centre for Applied Scientific Computing, Lawrence Livermore National Laboratory.
25. Hoffman, Matthew D., Gelman, Andrew, The No-U-turn sampler: Adaptively setting path lengths in Hamiltonian Monte Carlo. J. Mach. Learn. Res. 15:1 (2014), 1593–1623.
26. Hsu, Elton P., Stochastic Analysis on Manifolds. Graduate Studies in Mathematics. 2002, American Mathematical Society, Providence, RI.
27. Mudigonda, Mayur, Sohl-Dickstein, Jascha, Deweese, Michael, Hamiltonian Monte Carlo without detailed balance. Jebara, Tony, Xing, Eric P., (eds.) Proceedings of the 31st International Conference on Machine Learning (ICML-14) JMLR Workshop and Conference Proceedings, 2014, 719–726.
28. Lan, Shiwei, Zhou, Bo, Shahbaba, Babak, Spherical Hamiltonian Monte Carlo for constrained target distributions. ICML, vol. 31, 2014, 629–637.
29. Leimkuhler, B., Reich, Sebastian, Simulating Hamiltonian dynamics. 2004, Cambridge University Press.
30. Livingstone, S., Girolami, M., Information-Geometric Markov Chain Monte Carlo Methods Using Diffusions. Entropy 16 (2014), 3074–3102.
31. Mengersen, K.L., Tweedie, R.L., Rates of convergence of the Hastings and Metropolis algorithms. Ann. Stat. 1 (1996), 101–121.
32. Nash, John, The imbedding problem for Riemannian manifolds. Ann. Math. 63:1 (1956), 20–63.
33. Neal, Radford M., MCMC using Hamiltonian dynamics. Handbook of Markov Chain Monte Carlo, 54, 2010, 113–162.
34. Nocedal, J., Wright, S.J., Numerical Optimization. 2nd edition, 2006, Springer, New York.
35. Pasarica, Cristian, Gelman, Andrew, Adaptively scaling the Metropolis algorithm using expected squared jumped distance. Stat. Sin. 20 (2010), 343–364.
36. Penny, W.D., Litvak, V., Fuentemilla, L., Duzel, E., Friston, K., Dynamic causal models for phase coupling. J. Neurosci. Methods 183:1 (2009), 19–30 (Sep).
37. Raftery, Adrian E., Lewis, Steven, How many iterations in the Gibbs sampler?. Bayesian Statistics 4, 1992, Oxford University Press, 763–773.
38. Rasmussen, Carl Edward, Williams, Christopher K.I., Gaussian Processes for Machine Learning. 2005, The MIT Press.
39. Robert, Christian P., Casella, George, Monte Carlo Statistical Methods. 2005, Springer-Verlag New York, Inc., Secaucus, NJ, USA 0387212396.
40. Roberts, G., Tweedie, R., Exponential convergence of Langevin distributions and their discrete approximations. Bernoulli 2:4 (1996), 341–363.
41. Sengupta, B., Friston, K.J., Penny, W.D., Efficient gradient computation for dynamical models. NeuroImage 98 (2014), 521–527.
42. Sengupta, Biswa, Friston Karl, J., Penny Will, D., Second order MCMC for dynamic causal modelling, 2015 (in preparation).
43. Sengupta, Biswa, Friston, Karl J., Penny, Will D., Gradient-free MCMC methods for dynamic causal modelling. NeuroImage 15:112 (2015), 375–381 (Mar).
44. Srinivas, Niranjan, Krause, Andreas, Kakade, Sham, Seeger, Matthias, Gaussian process optimization in the bandit setting: No regret and experimental design. ICML, vol. 27, 2010, 1015–1022.
45. Srinivas, Niranjan, Krause, Andreas, Kakade, Sham, Seeger, Matthias, Information-theoretic regret bounds for Gaussian process optimization in the bandit setting. IEEE Trans. Inf. Theory 58:5 (2012), 3250–3265.
46. Stan Development Team, Stan Modeling Language Users Guide and Reference Manual, Version 2.5.0. 2014.
47. Wainwright, Martin J., Jordan, Michael I., Graphical models, exponential families, and variational inference. Found. Trends Mach. Learn. 1935-8237, 1(1-2), 2008, 1–305.
48. Wang, Ziyu, Mohamed, Shakir, de Freitas, Nando, Adaptive Hamiltonian and Riemann manifold Monte Carlo. ICML, vol. 28, 2013, 1462–1470.
49. Xifara, T., Sherlock, C., Livingstone, S., Byrne, S., Girolami, M., Langevin diffusions and the Metropolis-adjusted Langevin algorithm. Statistics & Probability Letters. 91 (2014), 14–19.