Local loss optimization in operator models: A new insight into spectral learning

Proceedings of the 29th International Conference on Machine Learning, ICML 2012

Volumn 2, Issue , 2012, Pages 1879-1886

  Balle, Borja ^a   Quattoni, Ariadna ^a   Carreras, Xavier ^a  

^a UNIVERSITAT POLITÈCNICA DE CATALUNYA   (Spain)

Author keywords

[No Author keywords available]

Indexed keywords

CONVEX RELAXATION; DISCRETE NUMBERS; FINITE SUBSETS; HIGH PROBABILITY; LATENT VARIABLE MODELS; LOCAL LOSS; MODEL COMPLEXITY; NONCONVEX OPTIMIZATION; OPERATOR MODEL; RANDOMIZED STRATEGY; REGULARIZATION PARAMETERS; SPECTRAL LEARNING; SPECTRAL METHODS;

CONVEX OPTIMIZATION; LEARNING SYSTEMS; RELAXATION PROCESSES; SPECTROSCOPY;

OPTIMIZATION;

EID: 84867131562     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (12)

1. Bailly, R. Quadratic weighted automata: Spectral algorithm and likelihood maximization. Journal of Machine Learning Research, 2011.
2. Balle, B., Quattoni, A., and Carreras, X. A spectral learning algorithm for finite state transducers. ECMLPKDD, 2011.
3. Beimel, A., Bergadano, F., Bshouty, N.H., Kushilevitz, E., and Varricchio, S. Learning functions represented as multiplicity automata. JACM, 2000.
4. Boots, B., Siddiqi, S., and Gordon, G. Closing the learning planning loop with predictive state representations. I. J. Robotic Research, 2011.
5. Dempster, A. P., Laird, N. M., and Rubin, D. B. Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society, 1977.
6. Hsu, D., Kakade, S. M., and Zhang, T. A spectral algorithm for learning hidden markov models. In Proc. of COLT, 2009.
7. Liu, G., Sun, J., and Yan, S. Closed-form solutions to a category of nuclear norm minimization problems. NIPS Workshop on Low-Rank Methods for Large-Scale Machine Learning, 2010.
8. Luque, F.M., Quattoni, A., Balle, B., and Carreras, X. Spectral learning in non-deterministic dependency parsing. EACL, 2012.
9. Parikh, A.P., Song, L., and Xing, E.P. A spectral algorithm for latent tree graphical models. ICML, 2011.
10. Siddiqi, S.M., Boots, B., and Gordon, G.J. Reduced-rank hidden markov models. AISTATS, 2010.
11. Song, L., Boots, B., Siddiqi, S., Gordon, G., and Smola, A. Hilbert space embeddings of hidden markov models. ICML, 2010.
12. Vershynin, R. Introduction to the non-asymptotic analysis of random matrices, volume Compressed Sensing, Theory and Applications, chapter 5. CUP, 2012.