Self-paced learning: An implicit regularization perspective

31st AAAI Conference on Artificial Intelligence, AAAI 2017

Volumn , Issue , 2017, Pages 1877-1883

  Fan, Yanbo ^a,d   He, Ran ^a,b,c,d   Liang, Jian ^a,b,d   Hu, Baogang ^a,d  

^a INSTITUTE OF AUTOMATION   (China)

^b CASIA   (China)

^c Shenzhen Fundamental Research Institutions   (China)

^d UNIVERSITY OF CHINESE ACADEMY OF SCIENCES   (China)

Author keywords

[No Author keywords available]

Indexed keywords

QUADRATIC PROGRAMMING;

COGNITIVE MECHANISMS; EXPLICIT FORM; HALF-QUADRATIC OPTIMIZATIONS; LEARNING PROCEDURES; LOSS FUNCTIONS; SELF-PACED LEARNING; WEIGHTING STRATEGIES; WORKING MECHANISMS;

ARTIFICIAL INTELLIGENCE;

EID: 85030459062     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (34)

1. Bengio, Y.; Louradour, J.; Collobert, R.; and Weston, J. 2009. Curriculum learning. In ICML, 41-48.
2. Chang, C.-C., and Lin, C.-J. 2011. Libsvm: a library for support vector machines. ACM Transactions on Intelligent Systems and Technology 2(3):27.
3. Chen, B.; Liu, X.; Zhao, H.; and Príncipe, J. C. 2016a. Maximum correntropy kalman filter. Automatica, forthcoming.
4. Chen, B.; Xing, L.; Zhao, H.; Zheng, N.; and Príncipe, J. C. 2016b. Generalized correntropy for robust adaptive filtering. TSP 64(13):3376-3387.
5. Fan, R.-E.; Chang, K.-W.; Hsieh, C.-J.; Wang, X.-R.; and Lin, C.-J. 2008. Liblinear: A library for large linear classification. JMLR 9:1871-1874.
6. Geman, D., and Reynolds, G. 1992. Constrained restoration and the recovery of discontinuities. TPAMI 14(3):367-383.
7. Geman, D., and Yang, C. 1995. Nonlinear image recovery with half-quadratic regularization. TIP 4(7):932-946.
8. He, R.; Hu, B.; Yuan, X.; and Wang, L. 2014a. Robust recognition via information theoretic learning. Springer.
9. He, R.; Zheng, W.-S.; Tan, T.; and Sun, Z. 2014b. Half-quadratic-based iterative minimization for robust sparse representation. TPAMI 36(2):261-275.
10. He, R.; Tan, T.; and Wang, L. 2014. Robust recovery of corrupted low-rank matrix by implicit regularizers. TPAMI 36(4):770-783.
11. Hubert, L., and Arabie, P. 1985. Comparing partitions. Journal of Classification 2(1):193-218.
12. Jiang, L.; Meng, D.; Mitamura, T.; and Hauptmann, A. G. 2014a. Easy samples first: Self-paced reranking for zero-example multimedia search. In ACM MM, 547-556.
13. Jiang, L.; Meng, D.; Yu, S.-I.; Lan, Z.; Shan, S.; and Hauptmann, A. 2014b. Self-paced learning with diversity. In NIPS, 2078-2086.
14. Jiang, L.; Meng, D.; Zhao, Q.; Shan, S.; and Hauptmann, A. G. 2015. Self-paced curriculum learning. In AAAI, 2694-2700.
15. Kumar, M. P.; Packer, B.; and Koller, D. 2010. Self-paced learning for latent variable models. In NIPS, 1189-1197.
16. Lee, Y. J., and Grauman, K. 2011. Learning the easy things first: Self-paced visual category discovery. In CVPR, 1721-1728.
17. Li, H.; Gong, M.; Meng, D.; and Miao, Q. 2016. Multi-objective self-paced learning. In AAAI, 1802-1808.
18. Liang, J.; Li, Z.; Cao, D.; He, R.; and Wang, J. 2016. Self-paced cross-modal subspace matching. In SIGIR, 569-578.
19. Mahoney, M. W., and Orecchia, L. 2011. Implementing regularization implicitly via approximate eigenvector computation. In ICML, 121-128.
20. Mahoney, M. W. 2012. Approximate computation and implicit regularization for very large-scale data analysis. In PODS, 143-154.
21. Meng, D., and Zhao, Q. 2015. What objective does self-paced learning indeed optimize? arXiv preprint arXiv:1511.06049.
22. Nikolova, M., and Chan, R. H. 2007. The equivalence of half-quadratic minimization and the gradient linearization iteration. TIP 16(6):1623-1627.
23. Nikolova, M., and Ng, M. K. 2005. Analysis of half-quadratic minimization methods for signal and image recovery. SIAM Journal on Scientific Computing 27(3):937-966.
24. Rockafellar, R. T. 2015. Convex analysis. Princeton university press.
25. Salakhutdinov, R., and Mnih, A. 2008. Probabilistic matrix factorization. In NIPS, 1-8.
26. Supancic, J. S., and Ramanan, D. 2013. Self-paced learning for long-term tracking. In CVPR, 2379-2386.
27. Vaida, F. 2005. Parameter convergence for em and mm algorithms. Statistica Sinica 831-840.
28. Wang, N.; Yao, T.; Wang, J.; and Yeung, D.-Y. 2012. A probabilistic approach to robust matrix factorization. In ECCV, 126-139.
29. Xu, C.; Tao, D.; and Xu, C. 2013. A survey on multi-view learning. arXiv preprint arXiv:1304.5634.
30. Xu, C.; Tao, D.; and Xu, C. 2015. Multi-view self-paced learning for clustering. In IJCAI, 3974-3980.
31. Yuan, X.-T., and Hu, B.-G. 2009. Robust feature extraction via information theoretic learning. In ICML, 1193-1200.
32. Zhang, D.; Meng, D.; Li, C.; Jiang, L.; Zhao, Q.; and Han, J. 2015. A self-paced multiple-instance learning framework for co-saliency detection. In ICCV, 594-602.
33. Zhang, D.; Meng, D.; Zhao, L.; and Han, J. 2016. Bridging saliency detection to weakly supervised object detection based on self-paced curriculum learning. In IJCAI, 3538-3544.
34. Zhao, Q.; Meng, D.; Jiang, L.; Xie, Q.; Xu, Z.; and Hauptmann, A. G. 2015. Self-paced learning for matrix factorization. In AAAI, 3196-3202.