Local Rademacher Complexity: Sharper risk bounds with and without unlabeled samples

Neural Networks

Volumn 65, Issue , 2015, Pages 115-125

  Oneto, Luca ^a   Ghio, Alessandro ^b   Ridella, Sandro ^a   Anguita, Davide ^b  

^a UNIVERSITY OF GENOA   (Italy)

^b UNIVERSITY OF GENOA   (Italy)

Author keywords

Local rademacher complexity; Performance estimation; Statistical learning theory; Unlabeled samples

Indexed keywords

COGNITIVE SYSTEMS;

GENERALIZATION ABILITY; PERFORMANCE ESTIMATION; RADEMACHER COMPLEXITY; RISK BOUNDS; STATE OF THE ART; STATISTICAL LEARNING THEORY; UNLABELED SAMPLES;

ARTIFICIAL INTELLIGENCE;

ARTICLE; CALCULATION; LEARNING ALGORITHM; MATHEMATICAL ANALYSIS; MATHEMATICAL MODEL; PRIORITY JOURNAL; PROBABILITY; ARTIFICIAL INTELLIGENCE; STATISTICAL MODEL;

ARTIFICIAL INTELLIGENCE; MODELS, STATISTICAL;

EID: 84923326912     PISSN: 08936080     EISSN: 18792782     Source Type: Journal    
DOI: 10.1016/j.neunet.2015.02.006     Document Type: Article

References (30)

1. Anguita D., Ghio A., Oneto L., Ridella S. The impact of unlabeled patterns in Rademacher complexity theory for kernel classifiers. Neural information processing systems 2011, 585-593.
2. Audibert J.Y., Tsybakov A.B. Fast learning rates for plug-in classifiers. The Annals of Statistics 2007, 35:608-633.
3. Bartlett P.L., Boucheron S., Lugosi G. Model selection and error estimation. Machine Learning 2002, 48:85-113.
4. Bartlett P.L., Bousquet O., Mendelson S. Localized Rademacher complexities. Computational learning theory 2002.
5. Bartlett P.L., Bousquet O., Mendelson S. Local Rademacher complexities. The Annals of Statistics 2005, 33:1497-1537.
6. Bartlett P.L., Mendelson S. Rademacher and Gaussian complexities: risk bounds and structural results. The Journal of Machine Learning Research 2003, 3:463-482.
7. Blanchard G., Massart P. Discussion: local Rademacher complexities and oracle inequalities in risk minimization. The Annals of Statistics 2006, 34:2664-2671.
8. Boucheron S., Lugosi G., Massart P. A sharp concentration inequality with applications. Random Structures & Algorithms 2000, 16:277-292.
9. Boucheron S., Lugosi G., Massart P. Concentration inequalities: a nonasymptotic theory of independence 2013, Oxford University Press.
10. Bousquet O. A bennett concentration inequality and its application to suprema of empirical processes. Comptes Rendus Mathematique 2002, 334:495-500.
11. Bousquet O., Boucheron S., Lugosi G. Introduction to statistical learning theory. Advanced lectures on machine learning 2004.
12. Bousquet O., Elisseeff A. Stability and generalization. The Journal of Machine Learning Research 2002, 2:499-526.
13. Chapelle O., Schölkopf B., Zien A. Semi-supervised learning 2006, MIT Press, Cambridge.
14. Cortes C., Kloft M., Mohri M. Learning kernels using local Rademacher complexity. Neural information processing systems 2013.
15. Kloft M., Blanchard G. The local Rademacher complexity of lp-norm multiple kernel learning. Neural information processing systems 2011.
16. Koltchinskii V. Local Rademacher complexities and oracle inequalities in risk minimization. The Annals of Statistics 2006, 34:2593-2656.
17. Koltchinskii V. Oracle inequalities in empirical risk minimization and sparse recovery problems 2011, Springer.
18. Ledoux M., Talagrand M. Probability in Banach spaces: isoperimetry and processes. Vol. 23 1991, Springer.
19. Lever G., Laviolette F., Shawe-Taylor J. Tighter PAC-Bayes bounds through distribution-dependent priors. Theoretical Computer Science 2013, 473:4-28.
20. McAllester D., Akinbiyi T. PAC-Bayesian theory. Empirical inference 2013, 95-103.
21. McDiarmid C. On the method of bounded differences. Surveys in combinatorics. Vol. 141 1989, 148-188.
22. Oneto L., Ghio A., Anguita S., Ridella S. An improved analysis of the Rademacher data-dependent bound using its self bounding property. Neural Networks 2013, 44:107-111.
23. Parrado-Hernández E., Ambroladze A., Shawe-Taylor J., Sun S. PAC-Bayes bounds with data dependent priors. The Journal of Machine Learning Research 2012, 13:3507-3531.
24. Rosasco L., De Vito E., Caponnetto A., Piana M., Verri A. Are loss functions all the same?. Neural Computation 2004, 16:1063-1076.
25. Srebro N., Sridharan K., Tewari A. Smoothness, low noise and fast rates. Neural information processing systems 2010.
26. Steinwart I., Scovel C. Fast rates for support vector machines using Gaussian kernels. The Annals of Statistics 2007, 35:575-607.
27. Talagrand M. The Glivenko-Cantelli problem. The Annals of Probability 1987, 15:837-870.
28. Valiant L. Probably approximately correct: nature's algorithms for learning and prospering in a complex world 2013, Basic Books.
29. Vapnik V.N. Statistical learning theory 1998, Wiley-Interscience.
30. Weisstein, E.W. (2013). Lambert W-Function. From MathWorld-A Wolfram Web Resource. http://mathworld.wolfram.com/LambertW-Function.html.