Rademacher complexities and bounding the excess risk in active learning

Journal of Machine Learning Research

Volumn 11, Issue , 2010, Pages 2457-2485

  Koltchinskii, Vladimir ^a  

^a GEORGIA INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

Active learning; Capacity function; Disagreement coefficient; Excess risk; Rademacher complexities

Indexed keywords

ACTIVE LEARNING; CAPACITY FUNCTION; DISAGREEMENT COEFFICIENT; EXCESS RISK; RADEMACHER COMPLEXITY;

RISK PERCEPTION;

LEARNING ALGORITHMS;

EID: 78649426154     PISSN: 15324435     EISSN: 15337928     Source Type: Journal    
DOI: None     Document Type: Article

References (21)

1. M.-F. Balcan, S. Hanneke and J. Wortman. The true sample complexity of active learning. In: Proc. 21st Annual Conference on Learning Theory (COLT 2008), pages 45-56, 2008.
2. M.-F. Balcan, A. Beygelzimer and J. Langford. Agnostic active learning. J. of Computer and System Sciences, 75 (1):78-89, 2009.
3. P. Bartlett, S. Boucheron and G. Lugosi. Model selection and error estimation. Machine Learning, 48:85-113, 2002.
4. P. Bartlett, O. Bousquet and S. Mendelson. Local Rademacher complexities. Annals of Statistics, 33 (4):1497-1537, 2005.
5. A. Beygelzimer, S. Dasgupta and J. Langford. Importance weighted active learning. In Proceedings of the 26th International Conference on Machine Learning ICML 2009, pages 49-56, Montreal, Canada, 2009.
6. R. Castro, R. Willett and R. Nowak. Faster rates in regression via active learning. In: Advances in Neural Information Processing Systems 18 (NIPS 2005), pages 179-186, 2005.
7. R. Castro and R. Nowak. Minimax bounds for active learning. IEEE Transactions on Information Theory, 54 (5):2339-2353, 2008.
8. S. Dasgupta, D. Hsu and C. Monteleoni. A general agnostic active learning algorithm. In: Advances in Neural Information Processing Systems 20 (NIPS 2007), pages 353-360, 2007.
9. L. Devroye, L. Györfi and G. Lugosi. A Probabilistic Theory of Pattern Recognition. Springer, New York, 1996.
10. R. M. Dudley. Uniform Central Limit Theorems. Cambridge University Press, 1999.
11. E. Giné and V. Koltchinskii. Concentration inequalities and asymptotic results for ratio type empirical processes. Annals of Probability, 34 (3):1143-1216, 2006.
12. E. J. Friedman. Active learning for smooth problems, In Proceeding of the 22nd Annual Conference on Learning Theory, COLT 2009, pages 343-352, Montreal, Canada, 2009.
13. S. Hanneke. Adaptive rates of convergence in active learning. In: Proc. 22nd Annual Conference on Learning Theory, COLT 2009, pages 353-364, Montreal, Canada, 2009a.
14. S. Hanneke. Rates of convergence in active learning. Preprint, 2009b.
15. V. Koltchinskii. Rademacher penalties and structural risk minimization. IEEE Transactions on Information Theory, 47 (5):1902-1914, 2001.
16. V. Koltchinskii. Local Rademacher complexities and oracle inequalities in risk minimization. Annals of Statistics, 34 (6):2593-2656, 2006.
17. V. Koltchinskii. Oracle inequalities in empirical risk minimization and sparse recovery problems. Lecture Notes. Ecole d'ete de Probabilités de Saint-Flour 2008, Preprint, 2008.
18. V. Koltchinskii and D. Panchenko. Rademacher processes and bounding the risk of function learning. In: E. Giné, D. Mason and J. Wellner (Eds). High Dimensional Probability II, pages 443-459, Birkhäuser, Boston, 2000.
19. P. Massart and E. Nedelec. Risk bounds for statistical learning. Annals of Statistics, 34 (5):2326-2366, 2006.
20. A. Tsybakov. Optimal aggregation in statistical learning. Annals of Statistics, 32 (1):135-166, 2004.
21. A. van der Vaart and J. Wellner. Weak Convergence and Empirical Processes. Springer, New York, 1996.