Learnability of the superset label learning problem

31st International Conference on Machine Learning, ICML 2014

Volumn 5, Issue , 2014, Pages 3602-3610

  Liu, Li Ping ^a   Dietterich, Thomas G ^a  

^a Oregon State University   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ARTIFICIAL INTELLIGENCE; LEARNING SYSTEMS;

EMPIRICAL RISKS; LEARNABILITY; LEARNING PROBLEM; MULTI-CLASS CLASSIFIER; SAMPLE COMPLEXITY;

RISK ASSESSMENT;

EID: 84919830662     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (18)

1. Aly, M. Survey on multi-class classification methods, 2005.
2. Anthony, M. and Biggs, N. Computational Learning Theory. Cambridge University Press, 1997.
3. Ben-David, S., Cesa-Bianchi, N., Haussler, D., and Long, P. Characterizations of leamability for classes of {0,., n}-valued functions. Journal of Computer and System Sciences, 50(l):74-86, 1995.
4. Blum, A. and Kalai, A. A note on learning from multiple-instance examples. Machine Learning, 30(l):23-29, 1998.
5. Briggs, R, Fern, X. Z., and Raich, R. Rank-loss support instance machines for MIML instance annotation. In Proceedings of the 18th International Conference on Knowledge Discovery and Data Mining (KDD'12), pp. 534-542, 2012.
6. Cour, T., Sapp, B., and Taskar, B. Learning from partial labels. Journal of Machine Learning Research, 12(May): 1501-1536, 2011.
7. Daniely, A., Sabato, S., Ben-David, S., and Shalev-Shwartz, S. Muhiclass leamability and the ERM principle. In The 24rd Annual Conference on Learning Theory (COLT 11), pp. 207-232, 2011.
8. Jin, R. and Ghahramani, Z. Learning with multiple labels. In Advances in Neural Information Processing Systems 15 (N1PS'02), pp. 897-904, 2002.
9. Liu, L.-P. and Dietterich, T. G. A conditional multinomial mixture model for superset label learning. In Advances in Neural Information Processing Systems 25 (NIPS'12), pp. 557-565, 2012.
10. Long, P. M. and Tan, L. PAC learning axis-aligned rectangles with respect to product distributions from multiple-instance examples. Machine Learning, 30(1):7-21, 1998.
11. Mukherjee, I. and Schapire, R. E. A theory of muhiclass boosting. Journal of Machine Learning Research, 14 (Feb):437-497,2013.
12. Natarajan, B.K. On learning sets and functions. Machine Learning, 4(l):67-97, 1989.
13. Nguyen, N. and Caruana, R. Classication with partial labels. In Proceedings of the 14th International Conference on Knowledge Discovery and Data Min-ing(KDD'08), pp. 551-559, 2008.
14. Sabato, S. and Tishby, N. Homogeneous multi-instance learning with arbitrary dependence. In Proceeding of the 22nd Annual Conference on Learning Theory (COLT'09), pp. 93-104, 2009.
15. Wang, W. and Zhou, Z.-H. Leamability of multi-instance multi-label learning. Chinese Science Bulletin, 57(19): 2488-2491,2012.
16. Zhang, M.-L. Disambiguation-free partial label leaming. In Proceedings of the 14th SIAM International Conference on Data Mining (SDM'14), pp. 37-45, 2014.
17. Zhou, Z.-H. and Zhang, M.-L. Multi-instance multilabel leaming with application to scene classification. In Advances in Neural Information Processing Systems 19 (NIPS'06), pp. 1609-1616, 2006.
18. Zhou, Z.-H., Zhang, M.-L., Huang, S.-J., and Li, Y.-F. Multi-instance multi-label learning. Artificial Intelligence, 176(I):2291-2320, 2012.