Noise-Adaptive margin-based active learning and lower bounds under tsybakov noise condition

30th AAAI Conference on Artificial Intelligence, AAAI 2016

Volumn , Issue , 2016, Pages 2180-2186

  Wang, Yining ^a   Singh, Aarti ^a  

^a Carnegie Mellon University   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ARTIFICIAL INTELLIGENCE;

ACTIVE-LEARNING ALGORITHM; DATA DISTRIBUTION; ERROR CONVERGENCE; LABEL DISTRIBUTION; LINEAR SEPARATORS; POLY-LOGARITHMIC FACTORS; SELECTIVE SAMPLING; UNIFORM DISTRIBUTION;

LEARNING ALGORITHMS;

EID: 85007235945     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (24)

1. Angluin, D. 1988. Queries and concept learning. Machine learning 2(4):319-342.
2. Awasthi, P.; Bandeira, A.; Charikar, M.; Krishnaswamy, R.; Villar, S.; and Ward, R. 2014. The power of localization for efficiently learning linear separators with noise. In STOC.
3. Balcan, M.-F., and Long, P. 2013. Active and passive learning of linear separators under log-concave distributions. In COLT.
4. Balcan, M.-F.; Beygelzimer, A.; and Langford, J. 2006. Agnostic active learning. In ICML.
5. Balcan, M.-F.; Broder, A.; and Zhang, T. 2007. Margin based active learning. In COLT.
6. Castro, R., and Nowak, R. 2006. Upper and lower error bounds for active learning. In The 44th Annual Allerton Conference on Communication, Control and Computing.
7. Castro, R. M., and Nowak, R. D. 2008. Minimax bounds for active learning. IEEE Transactions on Information Theory 54(5):2339-2353.
8. Cohn, D.; Atlas, L.; and Ladner, R. 1994. Improving generalization with active learning. Machine Learning 15(2):201- 221.
9. Cohn, D. 1990. Neural network exploration using optimal experiment design. In NIPS.
10. Dasgupta, S.; Hsu, D.; and Monteleoni, C. 2007. A general agnostic active learning algorithm. In NIPS.
11. Dasgupta, S. 2005. Coarse sample complexity bounds for active learning. In NIPS.
12. Graham, R., and Sloane, N. 1980. Lower bounds for constant weight codes. IEEE Transactions on Information Theory 26(1):37-43.
13. Hanneke, S., and Yang, L. 2014. Minimax analysis of active learning. arXiv:1410.0996.
14. Hanneke, S. 2007. A bound on the label complexity of agnostic active learning. In ICML.
15. Hanneke, S. 2011. Rates of convergence in active learning. The Annals of Statistics 39(1):333-361.
16. Hanneke, S. to appear. Theory of disagreement-based active learning. Foundations and Trends in Machine Learning.
17. Juditsky, A., and Nesterov, Y. 2014. Primal-dual subgradient methods for minimizing uniformly convex functions. arXiv:1401.1792.
18. Mammen, E.; Tsybakov, A. B.; et al. 1999. Smooth discrimination analysis. The Annals of Statistics 27(6):1808-1829.
19. Ramdas, A., and Singh, A. 2013a. Algorithmic connections between active learning and stochastic convex optimization. In ALT.
20. Ramdas, A., and Singh, A. 2013b. Optimal rates for stochastic convex optimization under tsybakov noise condition. In ICML.
21. Tsybakov, A. B., and Zaiats, V. 2009. Introduction to nonparametric estimation, volume 11. Springer.
22. Tsybakov, A. B. 2004. Optimal aggregation of classifiers in statistical learning. Annals of Statistics 135-166.
23. Wang, Y., and Singh, A. 2014. Noise-adaptive margin-based active learning and lower bounds under tsybakov noise condition. arXiv:1406.5383.
24. Zhang, C., and Chaudhuri, K. 2014. Beyond disagreementbased agnostic active learning. In NIPS.