Asymptotic analysis of generative semi-supervised learning

ICML 2010 - Proceedings, 27th International Conference on Machine Learning

Volumn , Issue , 2010, Pages 295-302

  Dillon, Joshua V ^a   Balasubramanian, Krishnakumar ^a   Lebanon, Guy ^a  

^a Georgia Institute of Technology   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALTERNATIVE FRAMEWORK; COMPOSITE LIKELIHOOD; DISTRIBUTION-FREE; MODELING ACCURACY; NAIVE BAYES; REAL WORLD EXPERIMENT; SEMI-SUPERVISED LEARNING; SIMULATION STUDIES; STRUCTURED PREDICTION; TEXT CLASSIFICATION;

STRUCTURAL FRAMES; SUPERVISED LEARNING; TEXT PROCESSING;

ASYMPTOTIC ANALYSIS;

EID: 77956525937     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (13)

1. Balean, M. F. and Blum, A. A discriminative model for semi-supervised learning. Journal of the Association for Computing Machinery, 2010.
2. Ben-David, S., Lu, T., and Pal, D. Does unlabeled data provably help? worst-case analysis of the sample complexity of semi-supervised learning. In International Conference on Learning Theory, 2008.
3. Castelli, V. and Cover, T. M. The relative value of labeled and unlabeled samples in pattern recognition with an unknown mixing parameter. IEEE Transactions on Information Theory, 42(6):2102-2117, 1996.
4. Chapelle, O., Schölkopf, B., and Zien, A. (eds.). Semi-Supervised Learning. MIT Press, 2006.
5. Cohen, I. and Cozman, F. G. Risks of semi-supervised learning. In Semi-Supervised Learning. MIT press, 2006.
6. Dillon, J. and Lebanon, G. Statistical and computational tradeoffs in stochastic composite likelihood. In Proc. of the International Conference on Artificial Intelligence and Statistics, 2009.
7. Ferguson, T. S. A Course in Large Sample Theory. Chapman & Hall, 1996.
8. Liang, P. and Jordan, M. I. An asymptotic analysis of generative, discriminative, and pseudolikelihood estimators. In Proc. of the International Conference on Machine Learning, 2008.
9. MacKay, D. J. C. Equivalence of linear boltzmann chains and hidden markov models. Neural Computation, 8(1): 178-181, 1996.
10. Nigam, K., McCallum, A., Thrun, S., and Mitchell, T. Text classification from labeled and unlabeled documents using EM. Machine Learning, 39(2):103-134, 2000.
11. Singh, A., Nowak, R., and Zhu, X. Unlabeled data: Now it helps, now it doesnt. In Advances in Neural Information Processing Systems, 2008.
12. Sinha, K. and Belkin, M. The value of labeled and unlabeled examples when the model is imperfect. In Advances in Neural Information Processing Systems, 2008.
13. Zhang, Tong. The value of unlabeled data for classification problems. In Proc. of the International Conference on Machine Learning, 2000.