. Penn-treebank, Les résultats sur Penn-Treebank montrent que CH-PRFA fournit une bonne initialisation pour l'algorithme de BW car CH-PRFA+BW se classe premier

N. Abe, M. K. Et, and . 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

A. Anandkumar, R. Ge, D. Hsu, S. M. Kakade, and M. Telgarsky, 2014, «Tensor decompositions for learning latent variable models», Journal of Machine Learning Research, vol.15, issue.1, pp.2773-2832

A. Anandkumar, D. Hsu, and S. M. Kakade, «A method of moments for mixture models and hidden Markov models», Proceedings of the 25 th Annual Conference on Learning Theory, pp.33-34, 2012.

A. Anandkumar, N. Michael, A. K. Tang, and A. Swami, Distributed Algorithms for Learning and Cognitive Medium Access with Logarithmic Regret, IEEE Journal on Selected Areas in Communications, vol.29, issue.4, pp.731-745, 2011.
DOI : 10.1109/JSAC.2011.110406

M. C. Araújo, T. C. Saldanha, R. K. Galvão, T. Yoneyama, H. C. Chame et al., The successive projections algorithm for variable selection in spectroscopic multicomponent analysis, Chemometrics and Intelligent Laboratory Systems, vol.57, issue.2, pp.65-73, 2001.
DOI : 10.1016/S0169-7439(01)00119-8

S. Arora, R. Ge, Y. Halpern, D. M. Mimno, A. Moitra et al., «A practical algorithm for topic modeling with provable guarantees», dans Proceedings of the 30 th International Conference on Machine Learning, ICML 2013, pp.16-21, 2013.

S. Arora, R. Ge, R. Kannan, and A. Moitra, «Computing a nonnegative matrix factorization -provably», dans Proceedings of the 44 th Symposium on Theory of Computing Conference, STOC 2012, pp.145-162, 2012.

S. Arora, R. Ge, and A. Moitra, Learning Topic Models -- Going beyond SVD, 2012 IEEE 53rd Annual Symposium on Foundations of Computer Science, pp.1-10, 2012.
DOI : 10.1109/FOCS.2012.49

P. Auer, N. Cesa-bianchi, Y. Freund, and R. E. Schapire, The Nonstochastic Multiarmed Bandit Problem, SIAM Journal on Computing, vol.32, issue.1, pp.48-77, 2002.
DOI : 10.1137/S0097539701398375

R. Bailly, Méthodes spectrales pour l'inférence grammaticale probabiliste de langages stochastiques rationnels, 2011.

R. Bailly, «Quadratic weighted automata : Spectral algorithm and likelihood maximization», Journal of Machine Learning Research, vol.20, pp.147-162, 2011.

R. Bailly, F. Denis, and L. Ralaivola, Grammatical inference as a principal component analysis problem, Proceedings of the 26th Annual International Conference on Machine Learning, ICML '09, pp.14-18, 2009.
DOI : 10.1145/1553374.1553379

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

B. Balle, X. Carreras, F. M. Luque, and A. Quattoni, «Spectral learning of weighted automata -A forward-backward perspective», Machine Learning, pp.1-2, 2014.

B. Balle, J. Castro, and R. Gavaldà, Learning probabilistic automata: A study in state distinguishability, Theoretical Computer Science, vol.473, pp.46-60
DOI : 10.1016/j.tcs.2012.10.009

B. Balle, W. L. Hamilton, and J. Pineau, 2014b, «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.

B. Balle, M. Et, and . Mohri, 2012, «Spectral learning of general weighted automata via constrained matrix completion», dans Advances in Neural Information Processing Systems 25 : 26 th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting, pp.2168-2176, 2012.

B. Balle, P. Panangaden, and D. Precup, A Canonical Form for Weighted Automata and Applications to Approximate Minimization, 2015 30th Annual ACM/IEEE Symposium on Logic in Computer Science, pp.701-712, 2015.
DOI : 10.1109/LICS.2015.70

I. Bibliographie-balle, B. , A. Quattoni, and X. Carreras, «A spectral learning algorithm for finite state transducers», dans Machine Learning and Knowledge Discovery in Databases, pp.156-171, 2011.

B. Balle and A. , Quattoni et X. Carreras. 2012b, «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.

A. Beimel, F. Bergadano, N. H. Bshouty, E. Kushilevitz, and S. Varricchio, Learning functions represented as multiplicity automata, «Learning functions represented as multiplicity automata», pp.506-530, 2000.
DOI : 10.1145/337244.337257

F. Bergadano, S. Et, and . Varricchio, «Learning behaviors of automata from multiplicity and equivalence queries», dans Algorithms and Complexity, Second Italian Conference, CIAC '94 Proceedings, pp.54-62, 1994.

P. Blunsom, T. Et, and . Cohn, «A hierarchical pitman-yor process HMM for unsupervised part of speech induction», Proceedings of the 49 th Annual Meeting of the Association for Computational Linguistics : Human Language Technologies, pp.865-874, 2011.

J. W. Boardman, «Automating spectral unmixing of aviris data using convex geometry concepts», dans Summaries 4 th Annu, JPL Airborne Geoscience Workshop, vol.1, pp.93-119, 1993.

B. Boots, G. J. Et, and . Gordon, «An online spectral learning algorithm for partially observable nonlinear dynamical systems», Proceedings of the Twenty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2011, 2011.

B. Boots, G. J. Gordon, and A. Gretton, 2013, «Hilbert space embeddings of predictive state representations», Proceedings of the Twenty-Ninth Conference on Uncertainty in Artificial Intelligence, UAI 2013, 2013.

B. Boots, S. M. Siddiqi, and G. J. Gordon, «Closing the learning-planning loop with predictive state representations», th International Conference on Autonomous Agents and Multiagent Systems, pp.1369-1370, 2010.

B. Boots, S. M. Siddiqi, and G. J. Gordon, «Closing the learning-planning loop with predictive state representations», th International Conference on Autonomous Agents and Multiagent Systems, pp.1369-1370, 2010.

C. Boutsidis, E. Et, and . Gallopoulos, SVD based initialization: A head start for nonnegative matrix factorization, Pattern Recognition, vol.41, issue.4, pp.1350-1362, 2008.
DOI : 10.1016/j.patcog.2007.09.010

I. Bibliographie-bowling, M. H. , P. Mccracken, M. James, J. Neufeld et al., «Learning predictive state representations using non-blind policies», Machine Learning, Proceedings of the Twenty-Third International Conference, pp.129-136, 2006.

J. Cai, E. J. Candès, and Z. Shen, A Singular Value Thresholding Algorithm for Matrix Completion, SIAM Journal on Optimization, vol.20, issue.4, pp.1956-1982, 2010.
DOI : 10.1137/080738970

R. C. Carrasco, J. Et, and . Oncina, «Learning stochastic regular grammars by means of a state merging method», dans Grammatical Inference and Applications, Second International Colloquium, ICGI-94, Proceedings, pp.139-152, 1994.

R. C. Carrasco, J. Et, and . Oncina, Learning deterministic regular grammars from stochastic samples in polynomial time, RAIRO - Theoretical Informatics and Applications, vol.33, issue.1, pp.1-20, 1999.
DOI : 10.1051/ita:1999102

J. Castro, R. Et, and . Gavaldà, «Towards feasible pac-learning of probabilistic deterministic finite automata», dans Grammatical Inference : Algorithms and Applications , 9 th International Colloquium, Proceedings, pp.163-174, 2008.

Y. D. Castro, E. Gassiat, and S. L. Corff, 2015, «Consistent estimation of the filtering and marginal smoothing distributions in nonparametric hidden markov models»

T. Chan, W. Ma, A. Ambikapathi, and C. Chi, A Simplex Volume Maximization Framework for Hyperspectral Endmember Extraction, IEEE Transactions on Geoscience and Remote Sensing, vol.49, issue.11, pp.4177-4193, 2011.
DOI : 10.1109/TGRS.2011.2141672

T. Chan, W. Ma, C. Chi, and Y. Wang, A Convex Analysis Framework for Blind Separation of Non-Negative Sources, IEEE Transactions on Signal Processing, vol.56, issue.10, pp.5120-5134, 2008.
DOI : 10.1109/TSP.2008.928937

A. Çivril and M. Magdon-ismail, «On selecting a maximum volume sub-matrix of a matrix and related problems», Theor. Comput. Sci, vol.410, pp.47-49, 2009.

A. Clark and F. Thollard, «Pac-learnability of probabilistic deterministic finite state automata», Journal of Machine Learning Research, vol.5, pp.473-497, 2004.

I. Clarkson, «Optimal periodic sensor scheduling in Electronic Support», Proc. Defence Appl. Signal Process, 2005.

I. Clarkson and J. , Number/theoretic solutions to intercept time problems, IEEE Transactions on Information Theory, vol.42, issue.3, pp.959-971
DOI : 10.1109/18.490557

I. Clarkson, A. Et, and . Pollington, Performance limits of sensor-scheduling strategies in electronic support, IEEE Transactions on Aerospace and Electronic Systems, vol.43, issue.2, pp.645-650, 2007.
DOI : 10.1109/TAES.2007.4285359

I. V. Clarkson, «The arithmetic of receiver scheduling for Electronic Support», dans Aerospace Conference, Proceedings. 2003 IEEE, pp.2049-2064, 2003.

S. B. Cohen, K. Stratos, M. Collins, D. P. Foster, and L. H. Ungar, 2013, «Experiments with spectral learning of latent-variable PCfgs», dans Human Language Technologies : Conference of the North American Chapter of the Association of Computational Linguistics, Proceedings, pp.148-157, 2013.

N. Colombo, N. Et, and . Vlassis, «Stable spectral learning based on schur decomposition», Proceedings of the 31 st Conference on Uncertainty in Artificial Intelligence , UAI 2015, 2015.

I. Csiszár, G. Et, and . Tusnády, «Information geometry and alternating minimization procedures», Statistics & Decisions, issue.1, pp.205-237, 1984.

G. Cybenko and V. Crespi, Learning Hidden Markov Models Using Nonnegative Matrix Factorization, IEEE Transactions on Information Theory, vol.57, issue.6, pp.3963-3970, 2011.
DOI : 10.1109/TIT.2011.2132490

F. Denis, Y. Et, and . Esposito, «Identification in the limit of probabilistic non deterministic automata and undecidable problem for multiplicity automata», dans Proceedings of The 17 th Conference on Learning Theory, pp.1-4, 2004.

F. Denis, Y. Et, and . Esposito, «On rational stochastic languages», Fundam. Inform, vol.86, pp.1-2, 2008.

F. Denis, M. Gybels, and A. Habrard, 2014, «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.

W. Ding, P. Ishwar, and M. H. , Rohban et V. Saligrama. 2013a, «Necessary and sufficient conditions for novel word detection in separable topic models», p.7994, 1310.

W. Bibliographie-ding and P. , Ishwar et V. Saligrama. 2015a, «Necessary and sufficient conditions and a provably efficient algorithm for separable topic discovery»

W. Ding, P. Ishwar, and V. Saligrama, «A topic modeling approach to ranking», Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics, AISTATS 2015, 2015.

W. Ding, M. H. Rohban, P. Ishwar, and V. Saligrama, «Topic discovery through data dependent and random projections», Proceedings of the 30 th International Conference on Machine Learning, ICML 2013, pp.16-21, 2013.

W. Ding, M. H. Rohban, P. Ishwar, and V. Saligrama, 2014, «Efficient distributed topic modeling with provable guarantees», Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics, pp.167-175, 2014.

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

F. Doshi-velez, D. Pfau, F. Wood, and N. Roy, 2015, «Bayesian nonparametric methods for partially-observable reinforcement learning», Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol.37, issue.2, pp.394-407

P. Dupont, F. Denis, and Y. Esposito, Links between probabilistic automata and hidden Markov models: probability distributions, learning models and induction algorithms, Pattern Recognition, vol.38, issue.9, pp.1349-1371, 2005.
DOI : 10.1016/j.patcog.2004.03.020

B. Dutertre, Dynamic scan scheduling, 23rd IEEE Real-Time Systems Symposium, 2002. RTSS 2002., pp.3-5, 2002.
DOI : 10.1109/REAL.2002.1181586

E. D. El-mahassni, S. D. Howard, and I. V. Clarkson, «A Markov-chain model for sensor scheduling in electronic support», dans Signals, Systems and Computers, Conference Record of the Thirty-Eighth Asilomar Conference on, pp.2183-2187, 2004.

Y. Ephraim, N. Et, and . Merhav, Hidden Markov processes, IEEE Transactions on Information Theory, vol.48, issue.6, pp.1518-1569, 2002.
DOI : 10.1109/TIT.2002.1003838

Y. Esposito, Contribution à l'inférence d'automates probabilistes, 2004.

Y. Esposito, A. Lemay, F. Denis, and P. Dupont, «Learning probabilistic residual finite state automata», dans Grammatical Inference : Algorithms and Applications, 6 th International Colloquium : ICGI 2002, Proceedings, pp.77-91, 2002.

L. Finesso, A. Grassi, and P. Spreij, Approximation of stationary processes by hidden Markov models, Mathematics of Control, Signals, and Systems, vol.11, issue.1, pp.1-22, 2010.
DOI : 10.1007/s00498-010-0050-7

V. Bibliographie-fliess and M. , «Matrices de hankel», J. Math. Pures Appl, vol.53, issue.9, pp.197-222, 1974.

H. D. Friedman, Coincidence of Pulse Trains, Journal of Applied Physics, vol.25, issue.8, pp.1001-1005, 1954.
DOI : 10.1063/1.1721780

R. Gavaldà, P. W. Keller, J. Pineau, and D. Precup, PAC-Learning of Markov Models with Hidden State, Machine Learning : ECML 2006, 17 th European Conference on Machine Learning Proceedings, pp.150-161, 2006.
DOI : 10.1007/11871842_18

R. Ge, J. Et, and . Zou, 2015, «Intersecting faces : Non-negative matrix factorization with new guarantees», Proceedings of the 32 nd International Conference on Machine Learning, ICML 2015, pp.6-11, 2015.

N. Gillis, Robustness Analysis of Hottopixx, a Linear Programming Model for Factoring Nonnegative Matrices, SIAM Journal on Matrix Analysis and Applications, vol.34, issue.3, pp.1189-1212, 2013.
DOI : 10.1137/120900629

N. Gillis, Successive Nonnegative Projection Algorithm for Robust Nonnegative Blind Source Separation, SIAM Journal on Imaging Sciences, vol.7, issue.2, pp.1420-1450, 2014.
DOI : 10.1137/130946782

N. Gillis, «The why and how of nonnegative matrix factorization», 1401.

N. Gillis, R. Et, and . Luce, 2014, «Robust near-separable nonnegative matrix factorization using linear optimization», Journal of Machine Learning Research, vol.15, issue.1, pp.1249-1280

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

A. Gittens and J. A. Tropp, «Tail bounds for all eigenvalues of a sum of random matrices», p.4513, 2011.

H. Glaude and H. Boucard, 2015, «Method and system for determining a reception configuration and a duration of a time interval», WO Patent App

H. Glaude, C. Enderli, J. Grandin, and O. Pietquin, «Learning of scanning strategies for electronic support using predictive state representations», dans 25th IEEE, Machine Learning for Signal Processing MLSP 2015, pp.1-6, 2015.

H. Glaude, C. Enderli, and O. Pietquin, 2015c, «Non-negative spectral learning for linear sequential systems», dans Neural Information Processing -22nd International Conference Proceedings, Part II, pp.143-151, 2015.

H. Glaude, C. Enderli, and O. Pietquin, «Spectral learning with proper probabilities for finite state automaton», dans Automatic Speech Recognition and Understanding Workshop, 2015.

H. Glaude, O. Et, and . Pietquin, 2016, «Pac learning of probabilistic automaton based on the method of moments», Proceedings of the 33 rd International Conference on Machine Learning, ICML 2016, pp.19-24, 2016.

H. Glaude, O. Pietquin, and C. Enderli, 2014, «Subspace identification for predictive state representation by nuclear norm minimization», IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, pp.1-8, 2014.

E. M. Gold, Language identification in the limit, Information and Control, vol.10, issue.5, pp.447-474, 1967.
DOI : 10.1016/S0019-9958(67)91165-5

S. Gopalakrishnan, Sharp utilization thresholds for some realtime scheduling problems, ACM SIGMETRICS Performance Evaluation Review, vol.39, issue.4, pp.12-22, 2012.
DOI : 10.1145/2185395.2185398

S. Gopalakrishnan, M. Caccamo, and L. Sha, Sharp Thresholds for Scheduling Recurring Tasks with Distance Constraints, IEEE Transactions on Computers, vol.57, issue.3, pp.344-358, 2008.
DOI : 10.1109/TC.2007.70808

A. J. Gounalis, «System and method for non-maximum dwell duration selection for use in detecting emitter signals», G01S007/41, p.90, 1988.

A. J. Gounalis, «System and method for detecting and jamming emitter signals», G01S 7/38, pp.90-98, 2006.

A. J. Gounalis, «System and method for receiver resource allocation and verification», G01S 13/00, pp.89-342165, 2006.

A. J. Gounalis, «System and method for detection of emitter signals using multiple intercept rules», G01S 7/40, pp.90-98, 2007.

A. J. Gounalis, «System and method for detecting emitters signals having multivalued illumination times», G01S 13/00, pp.89-342195, 2008.

A. J. Gounalis, «Determining scan strategy for digital card», G01S 13/00, pp.89-342195, 2010.

O. Guttman, Probabilistic automata and distributions over sequences, 2006.

V. Bibliographie-gybels, M. , F. Denis, and A. Habrard, 2014, «Some improvements of the spectral learning approach for probabilistic grammatical inference», dans Proceedings of the 12 th International Conference on Grammatical Inference, pp.17-19, 2014.

A. Habrard, F. Denis, and Y. Esposito, «Using pseudo-stochastic rational languages in probabilistic grammatical inference», dans Grammatical Inference : Algorithms and Applications, 8 th International Colloquium, ICGI, Proceedings, pp.112-124, 2006.

W. L. Hamilton, M. M. Fard, and J. Pineau, 2013, «Modelling sparse dynamical systems with compressed predictive state representations», Proceedings of the 30 th International Conference on Machine Learning, ICML 2013, pp.16-21, 2013.

R. Hawkes, «The analysis of interception», Unpublished Defense Science and Technology Organisation Res, 1983.

A. Hefny, C. Downey, and G. J. Gordon, «A new view of predictive state methods for dynamical system learning», 2015.

C. De-la-higuera, F. Et, and . Thollard, «Identification in the limit with probability one of stochastic deterministic finite automata», dans Grammatical Inference : Algorithms and Applications, 5 th International Colloquium, Proceedings, pp.141-156, 2000.

D. Hsu, S. M. Kakade, and T. Zhang, A spectral algorithm for learning Hidden Markov Models, dans Proceedings of the 22 sn Annual Conference on Learning Theory, 2009.
DOI : 10.1016/j.jcss.2011.12.025

D. Hsu, S. M. Kakade, 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

H. Jaeger, Discrete Time, Discrete Valued Observable Operator Models : A Tutorial, 1998.

H. Jaeger, M. Zhao, K. Kretzschmar, T. Oberstein, D. Popovici et al., «Learning observable operator models via the es algorithm», New directions in statistical signal processing : From systems to brains, 2005.

E. Koksal, Periodic Search Strategies For Electronic Countermeasure Receivers With Desired Probability Of Intercept For Each Frequency Band, 2010.

A. Kulesza, N. Jiang, and S. Singh, «Low-rank spectral learning with weighted loss functions», Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics, AISTATS 2015, 2015.

A. Kulesza, N. Jiang, and S. Singh, «Spectral learning of predictive state representations with insufficient statistics», Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, pp.2715-2721, 2015.

A. Kulesza, N. R. Rao, and S. Singh, 2014, «Low-rank spectral learning», Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics, pp.522-530, 2014.

S. Kullback, R. A. Et, and . Leibler, «On information and sufficiency», The Annals of Mathematical Statistics, pp.79-86, 1951.

A. Kumar, V. Sindhwani, and P. Kambadur, 2013, «Fast conical hull algorithms for near-separable non-negative matrix factorization», Proceedings of the 30 th International Conference on Machine Learning, ICML 2013, pp.16-21, 2013.

S. Kunz, J. L. Twoey, B. L. Snedaker, R. Scheuerman, P. T. Coyne et al., «Methods and apparatus for creating a scan strategy», pp.13-89, 2010.

B. Lakshminarayanan, R. Et, and . Raich, 2010, «Non-negative matrix factorization for parameter estimation in hidden Markov models», Machine Learning for Signal Processing IEEE, pp.89-94, 2010.

D. D. Lee and H. S. Seung, «Learning the parts of objects by non-negative matrix factorization», Nature, vol.401, pp.6755-788, 1999.

W. L. Lewis, J. A. Et, and . Kardatzke, «Electronic support measures (ESM) duty dithering scheme for improved probability of intercept at low ESM utilization», G01S, vol.736, issue.342, p.17, 0162.

P. L?tstedt, Perturbation bounds for the linear least squares problem subject to linear inequality constraints, BIT, vol.13, issue.4, pp.500-519, 1983.
DOI : 10.1007/BF01933623

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

K. Liu, Q. Et, and . Zhao, Distributed Learning in Multi-Armed Bandit With Multiple Players, IEEE Transactions on Signal Processing, vol.58, issue.11, pp.5667-5681, 2010.
DOI : 10.1109/TSP.2010.2062509

X. Bibliographie-mackay and D. J. , «Ensemble learning for hidden Markov models», cahier de recherche, 1997.

M. P. Marcus, M. A. Marcinkiewicz, and B. Santorini, «Building a large annotated corpus of english : The penn treebank», Computational linguistics, pp.313-330, 1993.

C. Mcdiarmid, On the method of bounded differences, Surveys in Combinatorics, vol.141, issue.1, pp.148-188, 1989.
DOI : 10.1017/CBO9781107359949.008

K. Miller, R. Et, and . Schwarz, On the Interference of Pulse Trains, Journal of Applied Physics, vol.24, issue.8, pp.1032-1036, 1953.
DOI : 10.1063/1.1721430

J. Oncina, P. Et, and . García, «Identifying regular languages in polynomial time», Advances in Structural and Syntactic Pattern Recognition, pp.99-108, 1992.

R. Ortner, D. Ryabko, P. Auer, and R. Munos, Regret bounds for restless Markov bandits, Theoretical Computer Science, vol.558, pp.62-76, 2014.
DOI : 10.1016/j.tcs.2014.09.026

URL : https://hal.archives-ouvertes.fr/hal-00765450

N. Palmer, P. W. Et, and . Goldberg, «Pac-learnability of probabilistic deterministic finite state automata in terms of variation distance», dans Algorithmic Learning Theory, 16 th International Conference, ALT 2005 Proceedings, pp.157-170, 2005.

A. Quattoni, B. Balle, X. Carreras, and A. Globerson, «Spectral regularization for max-margin sequence tagging», Proceedings of the 31 th International Conference on Machine Learning, ICML 2014, pp.21-26, 2014.

B. Recht, C. Re, J. A. Tropp, and V. Bittorf, 2012, «Factoring nonnegative matrices with linear programs», dans Advances in Neural Information Processing Systems 25 : 26 th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting, pp.1223-1231, 2012.

H. Ren, C. Et, and . Chang, «Automatic spectral target recognition in hyperspectral imagery», IEEE Transactions on Aerospace and Electronic Systems, vol.39, issue.4, pp.1232-1249, 2003.

P. I. Richards, «Probability of coincidence for two periodically recurring events», The Annals of Mathematical Statistics, pp.16-29, 1948.

D. Ron, Y. Singer, and N. Tishby, «On the learnability and usage of acyclic probabilistic finite automata», Proceedings of the Eigth Annual Conference on Computational Learning Theory, COLT 1995, pp.31-40, 1995.

M. Rosencrantz, G. J. Gordon, and S. Thrun, Learning low dimensional predictive representations, Twenty-first international conference on Machine learning , ICML '04, 2004.
DOI : 10.1145/1015330.1015441

T. Rydén, EM versus Markov chain Monte Carlo for estimation of hidden Markov models: a computational perspective, Bayesian Analysis, vol.3, issue.4, pp.659-688, 2008.
DOI : 10.1214/08-BA326

A. G. Self, B. G. Et, and . Smith, Intercept time and its prediction, IEE Proceedings F Communications, Radar and Signal Processing, pp.215-220, 1985.
DOI : 10.1049/ip-f-1.1985.0052

A. Shaban, M. Farajtabar, B. Xie, and L. , Song et B. Boots. 2015, «Learning latent variable models by improving spectral solutions with exterior point methods», dans Proceedings of the Thirty-First Conference on Uncertainty in Artificial Intelligence, UAI 2015, 2015.

C. Shibata, R. Et, and . Yoshinaka, A comparison of collapsed Bayesian methods for probabilistic finite automata, Machine learning, pp.1-2, 2014.
DOI : 10.1007/s10994-013-5410-3

S. M. Siddiqi, B. Boots, and G. J. Gordon, «Reduced-rank hidden Markov models», Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pp.741-748, 2010.

J. Siffre, La guerre électronique : maître des ondes, maître du monde, Renseignement & guerre secr'ete, Lavauzelle, 2003.

J. Song, K. C. Et, and . Chen, Spectacle: fast chromatin state annotation using spectral learning, Genome Biology, vol.16, issue.1, p.33, 2015.
DOI : 10.1101/gr.097857.109

G. Stewart, J. Et, and . Guang-sun, Matrix perturbation theory, Computer science and scientific computing, 1990.

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

X. Bibliographie-teh and Y. W. , «A hierarchical Bayesian language model based on pitman-yor processes», st International Conference on Computational Linguistics and 44 th Annual Meeting of the Association for Computational Linguistics Proceedings of the Conference, pp.17-21, 2006.

C. Tekin, M. Et, and . Liu, Adaptive learning of uncontrolled restless bandits with logarithmic regret, 2011 49th Annual Allerton Conference on Communication, Control, and Computing (Allerton), pp.983-990, 2011.
DOI : 10.1109/Allerton.2011.6120273

C. Tekin, M. Et, and . Liu, Online Learning of Rested and Restless Bandits, IEEE Transactions on Information Theory, vol.58, issue.8, pp.5588-5611
DOI : 10.1109/TIT.2012.2198613

A. Tewari, M. J. Et, and . Giering, 2014, «Learning hidden Markov models using probabilistic matrix factorization», dans Data Mining for Service, pp.27-39

M. Thon and H. Jaeger, 2015, «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

B. Vanluyten, J. C. Willems, B. De, and . Moor, Structured nonnegative matrix factorization with applications to hidden Markov realization and clustering, Linear Algebra and its Applications, vol.429, issue.7, pp.1409-1424, 2008.
DOI : 10.1016/j.laa.2008.03.010

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, C. De, and . Higuera, 2012, «Results of the pautomac probabilistic automaton learning competition», Proceedings of the Eleventh International Conference on Grammatical Inference, ICGI 2012, pp.243-248, 2012.

E. Vidal, F. Thollard, C. De-la-higuera, F. Casacuberta, and R. C. Carrasco, Probabilistic finite-state machines - part II, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.27, issue.7, pp.1013-1025, 2005.
DOI : 10.1109/TPAMI.2005.148

URL : https://hal.archives-ouvertes.fr/ujm-00326250

P. Wedin, Perturbation bounds in connection with singular value decomposition, BIT, vol.2, issue.1, pp.99-111, 1972.
DOI : 10.1007/BF01932678

E. Wiewiora, Learning predictive representations from a history, Proceedings of the 22nd international conference on Machine learning , ICML '05, pp.964-971, 2005.
DOI : 10.1145/1102351.1102473

R. G. Wiley, ELINT : The Interception and Analysis of Radar Signals, 2006.

M. E. Winter, <title>N-FINDR: an algorithm for fast autonomous spectral end-member determination in hyperspectral data</title>, Imaging Spectrometry V, pp.266-275, 1999.
DOI : 10.1117/12.366289

B. Wolfe, M. R. James, and S. P. Singh, 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

W. Xu, X. Liu, and Y. Gong, Document clustering based on non-negative matrix factorization, Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval , SIGIR '03, pp.267-273, 2003.
DOI : 10.1145/860435.860485

Y. Xun, M. M. Kokar, and K. Baclawski, «Control based sensor management for a multiple radar monitoring scenario», Information Fusion, pp.49-63, 2004.

Z. Yang, E. Et, and . Oja, Quadratic nonnegative matrix factorization, Pattern Recognition, vol.45, issue.4, pp.1500-1510, 2012.
DOI : 10.1016/j.patcog.2011.10.014

H. Zhang, Z. Yang, and E. Oja, Adaptive multiplicative updates for quadratic nonnegative matrix factorization, Neurocomputing, vol.134, pp.206-213
DOI : 10.1016/j.neucom.2013.06.047

M. Zhao and H. Jaeger, Norm-Observable Operator Models, Neural Computation, vol.14, issue.1, pp.1927-1959, 2010.
DOI : 10.1162/neco.2009.01-08-687

M. Zhao, H. Jaeger, and M. Thon, A Bound on Modeling Error in Observable Operator Models and an Associated Learning Algorithm, Neural Computation, vol.39, issue.1, pp.2687-2712, 2009.
DOI : 10.1145/1329125.1329352

T. Zhou, J. A. Bilmes, and C. Guestrin, 2014, «Divide-and-conquer learning by anchoring a conical hull», dans Advances in Neural Information Processing Systems 27 : Annual Conference on Neural Information Processing Systems 2014, pp.1242-1250, 2014.