Smoothness, disagreement coefficient, and the label complexity of agnostic active learning

Journal of Machine Learning Research

Volumn 12, Issue , 2011, Pages 2269-2292

  Wang, Liwei ^a  

^a Peking University   (China)

Author keywords

Active learning; Disagreement coefficient; Label complexity; Smooth function

Indexed keywords

A-DENSITY; ACTIVE LEARNING; ACTIVE-LEARNING ALGORITHM; AGNOSTIC SETTING; CLASSIFICATION BOUNDARY; DATA DISTRIBUTION; DISAGREEMENT COEFFICIENT; HYPOTHESIS SPACE; LEARNING PROBLEM; SMOOTH FUNCTIONS; UPPER AND LOWER BOUNDS;

LEARNING ALGORITHMS;

LAKES;

EID: 80052202374     PISSN: 15324435     EISSN: 15337928     Source Type: Journal    
DOI: None     Document Type: Article

References (26)

1. M.-F. Balcan, A.Beygelzimer, and J. Langford. Agnostic active learning. In 23th International Conference on Machine Learning, 2006.
2. A. Beygelzimer, S. Dasgupta, and J. Langford. Importance weighted active learning. In 26th International Conference on Machine Learning, 2009.
3. A. Beygelzimer, D. Hsu, J. Langford, and T. Zhang. Agnostic active learning without constraints. In Advances in Neural Information Processing Systems, 2010.
4. M. Burnashev and K. Zigangirov. An interval estimation problem for controlled problem. Problems of Information Transmission, 10:223-231, 1974.
5. R. Castro and R. Nowak. Minimax bounds for active learning. IEEE Transactions on Information Theory, 54:2339-2353, 2008. (Pubitemid 351689563)
6. D. Cohn, L. Atlas, and R. Ladner. Improving generalization with active learning. Machine Learning, 15:201-221, 1994.
7. S. Dasgupta. Coarse sample complexity bounds for active learning. In Advances in Neural Information Processing Systems, 2005.
8. S. Dasgupta and J. Langford. A tutorial on active learning, 2009.
9. S. Dasgupta, D. Hsu, and C. Monteleoni. A general agnostic active learning algorithm. In Advances in Neural Information Processing Systems, 2007
10. R.M. Dudley. Uniform Central Limit Theorems. Cambridge University Press, 1999.
11. E. Friedman. Active learning for smooth problems. In 22th Annual Conference on Learning Theory, 2009.
12. A. Gorny. Contribution a l'etude des fonctions dérivables d'une variable réelle. Acta Mathematica, 13:317-358, 1939.
13. S. Hanneke. A bound on the label complexity of agnostic active learning. In 24th International Conference on Machine Learning, 2007.
14. S. Hanneke. Adaptive rates of convergence in active learning. In 22th Annual Conference on Learning Theory, 2009.
15. S. Hanneke. Rates of convergence in active learning. Annals of Statistics, 39:333-361, 2011.
16. M. Kääriäinen. Active learning in the non-realizable case. In 17th International Conference on Algorithmic Learning Theory, 2006.
17. A. Kolmogorov. Une généralisation de l'inégalite de J. Hadamard entre les bornes supérieurs des dérivés successives d'une fonction. C. R. Académie des Sciences, Paris, 207:763-765, 1938.
18. V. Koltchinskii. Local rademacher complexities and oracle inequalities in risk minimization. The Annals of Statistics, 34:2593-2656, 2006.
19. V. Koltchinskii. Rademacher complexities and bounding the excess risk in active learning. Journal of Machine Learning Research, 11:2457-2485, 2010.
20. E. Landau. Einige ungleichungen für zweimal differentiierbare funktionen. Proceedings of the London Mathematical Society, 13:43-49, 1913.
21. D.S. Mitrinović, J.E. Pečarié, and A.M. Fink. Inequalities Involving Functions and Their Integrals and Derivatives. Kluwer Academic Publishers, 1991.
22. I.J. Schoenberg. The elementary cases of landau's problem of inequlities between derivatives. The American Mathematical Monthly, 80:121-158, 1973.
23. A. Tsybakov. Optimal aggregation of classifiers in statistical learning. The Annals of Statistics, 32: 135-166, 2004. (Pubitemid 41449306)
24. A. van der Vaart and J. Wellner. Weak Convergence and Empirical Processes with Application to Statistics. Springer Verlag, 1996
25. V. Vapnik. Statistical Learning Theory. John Wiely and Sons, 1998.
26. L. Wang. Sufficient conditions for agnostic active learnable. In Advances in Neural Information Processing Systems, 2009.