Explicit learning curves for transduction and application to clustering and compression algorithms

Journal of Artificial Intelligence Research

Volumn 22, Issue , 2004, Pages 117-142

  Derbeko, Philip ^a   El Yaniv, Ran ^a   Meir, Ron ^a  

^a TECHNION ISRAEL INSTITUTE OF TECHNOLOGY   (Israel)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; DATA COMPRESSION; DATA REDUCTION; ERRORS; PROBLEM SOLVING; SET THEORY;

HYPOTHESIS SPACE; SUPPORT VECTOR MACHINES (SVMS); UNLABELED TEST POINTS;

ARTIFICIAL INTELLIGENCE;

EID: 24344495921     PISSN: 10769757     EISSN: 10769757     Source Type: Journal    
DOI: 10.1613/jair.1417     Document Type: Article

References (29)

1. Banerjee, A., & Langford, J. (2004). An objective evaluation criterion for clustering. Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD). Available at: http://hunch.net/~jl/projects/ prediction_bounds/clustering/clustering.ps.
2. Baram, Y., El-Yaniv, R., & Luz, K. (2004). Online choice of active learning algorithms. Journal of Machine Learning Research, 5, 255-291.
3. Bennett, K., & Demiriz, A. (1998). Semi-supervised support vector machines. Advances in Neural Information Processing Systems, 12, 368-374.
4. Blum, A., & Langford, J. (2003). PAC-MDL Bounds. In Proceedings of the Sixteenth Annual Conference on Computational Learning Theory, pp. 344-357.
5. Bottou, L., Cortes, C., & Vapnik, V. (1994). On the effective VC dimension. Tech. rep. bottou-effvc.ps.Z, Neuroprose (ftp://archive.cis.ohio- state.edu/pub/neuroprose). Also on http://leon.bottou.com/publications.
6. Boucheron, S., Lugosi, G., & Massart, P. (2003). Concentration inequalities using the entropy method. The Annals of Probability, 31, 1583-1614.
7. Cover, T., & Thomas, J. (1991). Elements of Information Theory. John Wiley & Sons, New York.
8. Dembo, A., & Zeitouni, O. (1998). Large Deviation Techniques and Applications (Second edition). Springer, New York.
9. Demiriz, A., & Bennett, K. (2000). Optimization approaches to semi-supervised learning. In Ferris, M., Mangasarian, O., & Pang, J. (Eds.), Complementarity: Applications, Algorithms and Extensions, Vol. 50 of Applied Optimization, chap. 1, pp. 1-19. Kluwer.
10. El-Yaniv, R., & Gerzon, L. (2004). Effective transductive learning via PAC-Bayesian model selection. Tech. rep. CS-2004-05, Technion - Israel Institute of Technology. Available at http://www.cs.technion.ac.il/Research/ TechnicalReports/index.html.
11. Herbrich, R. (2002). Learning Kernel Classifiers: Theory and Algorithms. MIT Press, Boston.
12. Hoeffding, W. (1963). Probability inequalities for sums of bounded random variables. J. Amer. Statis. Assoc., 58, 13-30.
13. Hush, D., & Scovel, C. (2003). Concentration of the hypergeometric distribution. Tech. rep. LA-UR-03-1353, Los Alamos National Laboratory.
14. Joachims, T. (1999). Transductive inference for text classification unsing support vector machines. In European Conference on Machine Learning.
15. Lanckriet, G., Cristianini, N., Ghaoui, L. E., Bartlett, P., & Jordan, M. (2002). Learning the kernel matrix with semi-definite programming. Tech. rep., University of Berkeley, Computer Science Division.
16. Langford, J., & Shawe-Taylor, J. (2002). PAC-Bayes and margins. In Advances in Neural Information Processing Systems (NIPS 2001), pp. 439-446.
17. Lugosi, G. (2003). Concentration-of-measure inequalities. Tech. rep., Department of Economics, Pompeu Fabra University. Machine Learning Summer School 2003, Australian National University. See http://www.econ.upf.es/lugosi/anu.ps.
18. McAllester, D. (1999). Some PAC-Bayesian theorems. Machine Learning, 37(3), 355-363.
19. McAllester, D. (2003a). PAC-Bayesian stochastic model selection. Machine Learning, 51(1), 5-21.
20. McAllester, D. (2003b). Simplified PAC-Bayesian margin bounds. In COLT, pp. 203-215.
21. McAllester, D. A. (1999). PAC-Bayesian model averaging. In Proceedings of the twelfth Annual conference on Computational learning theory, New York. ACM Press.
22. McDiarmid, C. (1989). On the method of bounded differences. In Surveys in Combinatorics, pp. 148-188. Cambridge University Press.
23. Seeger, M. (2002). Learning with labeled and unlabeled data. Tech. rep., Available at http://www.dai.ed.ac.uk/homes/seeger/papers/.
24. Seeger, M. (2003). Bayesian Gaussian process models: PAC-Bayesian generalization error bounds and sparse approximations. Ph.D. thesis, University of Edinburgh, Edinburgh.
25. Serfling, R. (1974). Probability inequalities for the sum in sampling without replacacement. The Annals of Statistics, 2(1), 39-48.
26. Vapnik, V. N. (1982). Estimation of Dependences Based on Empirical Data. Springer Verlag, New York.
27. Vapnik, V. N. (1995). The Nature of Statistical Learning Theory. Springer Verlag, New York.
28. Vapnik, V. N. (1998). Statistical Learning Theory. Wiley Interscience, New York.
29. Wu, D., Bennett, K., Cristianini, N., & Shawe-Taylor, J. (1999). Large margin trees for induction and transduction. In International Conference on Machine Learning.