N. Abe and M. K. Warmuth, On the computational complexity of approximating distributions by probabilistic automata, Proceedings of the Third Annual Workshop on Computational Learning Theory, COLT 1990, pp.52-66, 1990.
DOI : 10.1007/BF00992677

. Anandkumar, . Anima, . Ge, . Rong, . Hsu et al., Tensor decompositions for learning latent variable models, 1210.
DOI : 10.1007/978-3-319-24486-0_2

B. Balle, Learning finite-state machines: statistical and algorithmic aspects, 2013.

. Balle, . Borja, . Quattoni, . Ariadna, and X. Carreras, Local loss optimization in operator models: A new insight into spectral learning, Proceedings of the 29 th International Conference on Machine Learning, ICML 2012, 2012.

. Balle, . Borja, W. L. Hamilton, and J. Pineau, Methods of moments for learning stochastic languages: Unified presentation and empirical comparison, Proceedings of the 31 th International Conference on Machine Learning, ICML 2014, pp.21-26, 2014.

J. W. Carlyle and A. Paz, Realizations by stochastic finite automata, Journal of Computer and System Sciences, vol.5, issue.1, pp.26-40, 1971.
DOI : 10.1016/S0022-0000(71)80005-3

S. B. Cohen, . Stratos, . Karl, . Collins, . Michael et al., Experiments with spectral learning of latent-variable PCfgs, Human Language Technologies: Conference of the North American Chapter of the Association of Computational Linguistics, Proceedings, pp.148-157, 2013.

F. Denis and Y. Esposito, Learning Classes of Probabilistic Automata, pp.124-139, 2004.
DOI : 10.1007/978-3-540-27819-1_9

F. Denis and Y. Esposito, On rational stochastic languages, Fundam. Inform, vol.86, issue.12, pp.41-77, 2008.
DOI : 10.1007/11776420_22
URL : http://arxiv.org/abs/cs/0602062

F. Denis, M. Gybels, and A. Habrard, Dimension-free concentration bounds on Hankel matrices for spectral learning, Proceedings of the 31 th International Conference on Machine Learning, ICML 2014, pp.21-26, 2014.
URL : https://hal.archives-ouvertes.fr/hal-01009395

D. L. Donoho and V. Stodden, When does nonnegative matrix factorization give a correct decomposition into parts?, Advances in Neural Information Processing Systems 16 [Neural Information Processing Systems , NIPS 2003, pp.1141-1148, 2003.

Y. Esposito, ContributionàContribution`Contributionà l'inférence d'automates probabilistes, 2004.

D. P. Foster, . Rodu, . Jordan, . Ungar, and H. Lyle, Spectral dimensionality reduction for HMMs. CoRR, abs/1203, p.6130, 2012.

N. Gillis and S. A. Vavasis, Fast and Robust Recursive Algorithmsfor Separable Nonnegative Matrix Factorization, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.36, issue.4, pp.698-714, 2014.
DOI : 10.1109/TPAMI.2013.226
URL : http://arxiv.org/abs/1208.1237

N. Gillis, The why and how of nonnegative matrix factorization. CoRR, abs/1401, 2014.

H. Glaude, . Pietquin, . Olivier, and C. Enderli, Subspace identification for predictive state representation by nuclear norm minimization, 2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL), pp.1-8, 2014.
DOI : 10.1109/ADPRL.2014.7010609
URL : https://hal.archives-ouvertes.fr/hal-01104423

H. Glaude, C. Enderli, and O. Pietquin, Non-negative Spectral Learning for Linear Sequential Systems, Neural Information Processing -22 nd International Conference, ICONIP 2015 Proceedings, Part II, pp.143-151, 2015.
DOI : 10.1007/978-3-319-26535-3_17
URL : https://hal.archives-ouvertes.fr/hal-01225838

M. Gybels, . Denis, . François, and A. Habrard, Some improvements of the spectral learning approach for probabilistic grammatical inference, Proceedings of the 12 th International Conference on Grammatical Inference, ICGI 2014, pp.17-19, 2014.
URL : https://hal.archives-ouvertes.fr/hal-01075979

D. Hsu, . Kakade, M. Sham, and T. Zhang, A spectral algorithm for learning Hidden Markov Models, Journal of Computer and System Sciences, vol.78, issue.5, pp.1460-1480, 2012.
DOI : 10.1016/j.jcss.2011.12.025

M. J. Kearns, . Mansour, . Yishay, . Ron, . Dana et al., On the learnability of discrete distributions, Proceedings of the twenty-sixth annual ACM symposium on Theory of computing , STOC '94, pp.23-25, 1994.
DOI : 10.1145/195058.195155

E. Mossel and S. Roch, Learning nonsingular phylogenies and hidden markov models, Proceedings of the 37th Annual ACM Symposium on Theory of Computing, pp.366-375, 2005.
DOI : 10.1214/105051606000000024
URL : http://arxiv.org/abs/cs/0502076

. Sutskever, . Ilya, J. Martens, and G. E. Hinton, Generating text with recurrent neural networks, Proceedings of the 28 th International Conference on Machine Learning, ICML 2011, pp.1017-1024, 2011.

R. S. Sutton, . Barto, and G. Andrew, Reinforcement Learning: An Introduction, IEEE Transactions on Neural Networks, vol.9, issue.5, 1998.
DOI : 10.1109/TNN.1998.712192

M. Thon and H. Jaeger, Links between multiplicity automata, observable operator models and predictive state representations?a unified learning framework, Journal of Machine Learning Research, vol.16, pp.103-147, 2015.

. Verwer, . Sicco, . Eyraud, . Rémi, and C. Higuera, Results of the pautomac probabilistic automaton learning competition, Proceedings of the Eleventh International Conference on Grammatical Inference, ICGI 2012, pp.243-248, 2012.
URL : https://hal.archives-ouvertes.fr/hal-00833419

. Wolfe, J. Britton, M. R. Singh, and P. Satinder, Learning predictive state representations in dynamical systems without reset, Proceedings of the 22nd international conference on Machine learning , ICML '05, pp.980-987, 2005.
DOI : 10.1145/1102351.1102475