Spectral learning of dynamic systems from nonequilibrium data

Advances in Neural Information Processing Systems

Volumn , Issue , 2016, Pages 4186-4194

  Wu, Hao ^a   Noé, Frank ^a  

^a FREIE UNIVERSITÄT BERLIN   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

BINS; DYNAMICS; STOCHASTIC SYSTEMS;

CONSISTENT ESTIMATION; DISTRIBUTED DATA; EQUILIBRIUM CONSTRAINT; EQUILIBRIUM DYNAMICS; LINEAR COMPLEXITY; OBSERVABLE OPERATOR MODELS; SPECTRAL ALGORITHM; SPECTRAL LEARNING;

STOCHASTIC MODELS;

EID: 85014447006     PISSN: 10495258     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (30)

1. H. Jaeger, "Observable operator models for discrete stochastic time series," Neural Comput., Vol. 12, no. 6, pp. 1371-1398, 2000.
2. M.-J. Zhao, H. Jaeger, and M. Thon, "A bound on modeling error in observable operator models and an associated learning algorithm," Neural Comput., Vol. 21, no. 9, pp. 2687-2712, 2009.
3. H. Jaeger, "Discrete-time, discrete-valued observable operator models: a tutorial," tech. rep., International University Bremen, 2012.
4. M. L. Littman, R. S. Sutton, and S. Singh, "Predictive representations of state," in Adv. Neural. Inf. Process. Syst. 14 (NIPS 2001), pp. 1555-1561, 2001.
5. S. Singh, M. James, and M. Rudary, "Predictive state representations: A new theory for modeling dynamical systems," in Proc. 20th Conf. Uncertainty Artif. Intell. (UAI 2004), pp. 512-519, 2004.
6. E. Wiewiora, "Learning predictive representations from a history," in Proc. 22nd Intl. Conf. on Mach. Learn. (ICML 2005), pp. 964-971, 2005.
7. D. Hsu, S. M. Kakade, and T. Zhang, "A spectral algorithm for learning hidden Markov models," in Proc. 22nd Conf. Learning Theory (COLT 2009), pp. 964-971, 2005.
8. S. Siddiqi, B. Boots, and G. Gordon, "Reduced-rank hidden Markov models," in Proc. 13th Intl. Conf. Artif. Intell. Stat. (AISTATS 2010), Vol. 9, pp. 741-748, 2010.
9. A. Beimel, F. Bergadano, N. H. Bshouty, E. Kushilevitz, and S. Varricchio, "Learning functions represented as multiplicity automata," J. ACM, Vol. 47, no. 3, pp. 506-530, 2000.
10. M. Thon and H. Jaeger, "Links between multiplicity automata, observable operator, models and predictive state representations - a unified learning framework," J. Mach. Learn. Res., Vol. 16, pp. 103-147, 2015.
11. J.-H. Prinz, H. Wu, M. Sarich, B. Keller, M. Senne, M. Held, J. D. Chodera, C. Schütte, and F. Noé, "Markov models of molecular kinetics: Generation and validation," J. Chem. Phys., Vol. 134, p. 174105, 2011.
12. G. R. Bowman, V. S. Pande, and F. Noé, An introduction to Markov state models and their application to long timescale molecular simulation. Springer, 2013.
13. A. Ruttor, P. Batz, and M. Opper, "Approximate Gaussian process inference for the drift function in stochastic differential equations," in Adv. Neural. Inf. Process. Syst. 26 (NIPS 2013), pp. 2040-2048, 2013.
14. N. Schaudinnus, B. Bastian, R. Hegger, and G. Stock, "Multidimensional langevin modeling of nonoverdamped dynamics," Phys. Rev. Lett., Vol. 115, no. 5, p. 050602, 2015.
15. L. R. Rabiner, "A tutorial on hidden markov models and selected applications in speech recognition," Proc. IEEE, Vol. 77, no. 2, pp. 257-286, 1989.
16. F. Noé, H. Wu, J.-H. Prinz, and N. Plattner, "Projected and hidden markov models for calculating kinetics and metastable states of complex molecules," J. Chem. Phys., Vol. 139, p. 184114, 2013.
17. R. D. Turner, M. P. Deisenroth, and C. E. Rasmussen, "State-space inference and learning with Gaussian processes," in Proc. 13th Intl. Conf. Artif. Intell. Stat. (AISTATS 2010), pp. 868-875, 2010.
18. S. S. T. S. Andreas Svensson, Arno Solin, "Computationally efficient bayesian learning of Gaussian process state space models," in Proc. 19th Intl. Conf. Artif. Intell. Stat. (AISTATS 2016), pp. 213-221, 2016.
19. S. Hochreiter and J. Schmidhuber, "Long short-term memory," Neural Comp., Vol. 9, no. 8, pp. 1735-1780, 1997.
20. H. Wu, J.-H. Prinz, and F. Noé, "Projected metastable markov processes and their estimation with observable operator models," J. Chem. Phys., Vol. 143, no. 14, p. 144101, 2015.
21. M. Shirts and V. S. Pande, "Screen savers of the world unite," Science, Vol. 290, pp. 1903-1904, 2000.
22. T.-K. Huang and J. Schneider, "Spectral learning of hidden Markov models from dynamic and static data," in Proc. 30th Intl. Conf. on Mach. Learn. (ICML 2013), pp. 630-638, 2013.
23. M. K. Cowles and B. P. Carlin, "Markov chain monte carlo convergence diagnostics: a comparative review," J. Am. Stat. Assoc., Vol. 91, no. 434, pp. 883-904, 1996.
24. N. Jiang, A. Kulesza, and S. Singh, "Improving predictive state representations via gradient descent," in Proc. 30th AAAI Conf. Artif. Intell. (AAAI 2016), 2016.
25. H. Jaeger, "Modeling and learning continuous-valued stochastic processes with OOMs," Tech. Rep. GMD-102, German National Research Center for Information Technology (GMD), 2001.
26. B. Boots, S. M. Siddiqi, G. Gordon, and A. Smola, "Hilbert space embeddings of hidden markov models," in Proc. 27th Intl. Conf. on Mach. Learn. (ICML 2010), 2010.
27. M. Rosencrantz, G. Gordon, and S. Thrun, "Learning low dimensional predictive representations," in Proc. 22nd Intl. Conf. on Mach. Learn. (ICML 2004), pp. 88-95, ACM, 2004.
28. B. Boots, Spectral Approaches to Learning Predictive Representations. PhD thesis, Carnegie Mellon University, 2012.
29. H. Jaeger, M. Zhao, and A. Kolling, "Efficient estimation of OOMs," in Adv. Neural. Inf. Process. Syst. 18 (NIPS 2005), pp. 555-562, 2005.
30. G. Perez-Hernandez, F. Paul, T. Giorgino, G. De Fabritiis, and F. Noé, "Identification of slow molecular order parameters for markov model construction," J. Chem. Phys., Vol. 139, no. 1, p. 015102, 2013.