A. Anandkumar, R. Ge, D. Hsu, S. M. Kakade, and M. Telgarsky, Tensor decompositions for learning latent variable models. arXiv preprint arXiv:1210, p.7559, 2012.
DOI : 10.1007/978-3-319-24486-0_2

R. Bailly and F. Denis, Absolute convergence of rational series is semi-decidable, Information and Computation, vol.209, issue.3, pp.280-295, 2011.
DOI : 10.1016/j.ic.2010.11.004
URL : https://hal.archives-ouvertes.fr/hal-00359263

R. Bailly, A. Habrard, and F. Denis, A Spectral Approach for Probabilistic Grammatical Inference on Trees, Proc of ALT-10, pp.74-88, 2010.
DOI : 10.1007/978-3-642-16108-7_10
URL : https://hal.archives-ouvertes.fr/hal-00607096

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

B. Balle, W. Hamilton, and J. Pineau, Methods of moments for learning stochastic languages: Unified presentation and empirical comparison, Proc. of ICML-14, pp.1386-1394, 2014.

B. Balle, A. Quattoni, and X. Carreras, Local loss optimization in operator models: A new insight into spectral learning, Proc. of ICML, p.12, 2012.

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, K. Stratos, M. Collins, D. P. Foster, and L. H. Ungar, Experiments with spectral learning of latent-variable pcfgs, Proc of HLT-NAACL-13, pp.148-157, 2013.

F. Denis and Y. Esposito, On rational stochastic languages, Fundamenta Informaticae, vol.86, issue.1, pp.41-77, 2008.

N. Gillis, The Why and How of Nonnegative Matrix Factorization. ArXiv e-prints, 2014.

H. Glaude, O. Pietquin, and C. Enderli, Subspace identification for predictive state representation by nuclear norm minimization, 2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL), p.14, 2014.
DOI : 10.1109/ADPRL.2014.7010609
URL : https://hal.archives-ouvertes.fr/hal-01104423

A. E. Guterman, Rank and determinant functions for matrices over semirings, pp.1-33, 2007.
DOI : 10.1017/CBO9780511666315.002

M. Gybels, F. Denis, and A. Habrard, Some improvements of the spectral learning approach for probabilistic grammatical inference, Proc. of ICGI-12, pp.64-78, 2014.
URL : https://hal.archives-ouvertes.fr/hal-01075979

C. J. Lin, Projected Gradient Methods for Nonnegative Matrix Factorization, Neural Computation, vol.5, issue.10, pp.2756-2779, 2007.
DOI : 10.1007/BF01584660

M. Thon and H. Jaeger, Links between multiplicity automata, observable operator models and predictive state representationsa unified learning framework, Journal of Machine Learning Research

S. A. Vavasis, On the Complexity of Nonnegative Matrix Factorization, SIAM Journal on Optimization, vol.20, issue.3, pp.1364-1377, 2009.
DOI : 10.1137/070709967

S. Verwer, R. Eyraud, and C. De-la-higuera, Results of the pautomac probabilistic automaton learning competition, Journal of Machine Learning Research -Proceedings Track, vol.21, pp.243-248, 2012.
URL : https://hal.archives-ouvertes.fr/hal-00833419