On the robustness and generalization of Cauchy regression

ICIST 2014 - Proceedings of 2014 4th IEEE International Conference on Information Science and Technology

Volumn , Issue , 2014, Pages 100-105

  Liu, Tongliang ^a   Tao, Dacheng ^a  

^a UNIVERSITY OF TECHNOLOGY SYDNEY   (Australia)

Author keywords

Cauchy regression; covering number; generalization error bound; Rademacher complexity; robustness

Indexed keywords

BIG DATA; DIGITAL STORAGE; ERROR ANALYSIS; LEARNING ALGORITHMS; ROBUSTNESS (CONTROL SYSTEMS);

BREAKDOWN POINTS; CAUCHY REGRESSION; COVERING NUMBERS; GENERALIZATION ERROR BOUNDS; LEAST ABSOLUTE DEVIATIONS (LAD); OBJECTIVE FUNCTIONS; RADEMACHER COMPLEXITY; STATISTICAL PERFORMANCE;

DATA SHARING;

EID: 84910649016     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICIST.2014.6920341     Document Type: Conference Paper

References (19)

1. Nature, ISSN: 0028-0836, EISSN: 1476-4687, 2009.
2. James Manyika, Michael Chui, Brad Brown, Jacques Bughin, Richard Dobbs, Charles Roxburgh, and Angela H Byers. Big data: The next frontier for innovation, competition, and productivity. 2011.
3. Stephen Boyd, Neal Parikh, Eric Chu, Borja Peleato, and Jonathan Eckstein. Distributed optimization and statistical learning via the alternating direction method of multipliers. Foundations and Trends-R in Machine Learning, 3(1): 1-122, 2011.
4. Sameer Singh, Amarnag Subramanya, Fernando Pereira, and Andrew McCallum. Wikilinks: A large-scale cross-document coreference corpus labeled via links to wikipedia. Technical Report UM-CS-2012-015, University of Massachusetts, 2012.
5. Evan Sparks, Ameet Talwalkar, Virginia Smith, Xinghao Pan, Joseph Gonzalez, Tim Kraska, Michael I Jordan, and Michael J Franklin. Mli: An api for distributed machine learning. In International Conference on Data Mining (ICDM). IEEE, 2013.
6. Daniel D Lee and H Sebastian Seung. Learning the parts of objects by non-negative matrix factorization. Nature, 401(6755): 788-791, 1999.
7. Naiyang Guan, Dacheng Tao, Zhigang Luo, and John Shawe-Taylor. Mahnmf: Manhattan non-negative matrix factorization. arXiv preprint arXiv: 1207. 3438, 2012.
8. Peter J Huber. Robust statistics. Springer, 2011.
9. Harry Richard Moore et al. Robust regression using maximumlikelihood weighting and assuming cauchy-distributed random error. Technical Report DTIC Document, Naval Postgraduate School, 1977.
10. Ivan Mizera and Christine H Müller. Breakdown points of cauchy regression-scale estimators. Statistics &probability letters, 57(1): 79-89, 2002.
11. Vladimir Vapnik. The nature of statistical learning theory. Springer, 2000.
12. Tong Zhang. Covering number bounds of certain regularized linear function classes. The Journal of Machine Learning Research, 2: 527-550, 2002.
13. Peter L Bartlett and Shahar Mendelson. Rademacher and gaussian complexities: Risk bounds and structural results. The Journal of Machine Learning Research, 3: 463-482, 2003.
14. Andreas Christmann and Arnout Van Messem. Bouligand derivatives and robustness of support vector machines for regression. The Journal of Machine Learning Research, 9: 915-936, 2008.
15. Huan Xu and Shie Mannor. Robustness and generalization. Machine learning, 86(3): 391-423, 2012.
16. Martin Anthony and Peter L Bartlett. Neural network learning: Theoretical foundations. Cambridge university press, 2009.
17. Wassily Hoeffding. Probability inequalities for sums of bounded random variables. Journal of the American statistical association, 58(301): 13-30, 1963.
18. Colin McDiarmid. On the method of bounded differences. Surveys in combinatorics, 141(1): 148-188, 1989.
19. Shahar Mendelson. A few notes on statistical learning theory. In Advanced Lectures on Machine Learning, pages 1-40. Springer, 2003.