Local complexities for empirical risk minimization

Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)

Volumn 3120, Issue , 2004, Pages 270-284

  Bartlett, Peter L ^a   Mendelson, Shahar ^b   Philips, Petra ^b  

^a UNIVERSITY OF CALIFORNIA   (United States)

^b AUSTRALIAN NATIONAL UNIVERSITY   (Australia)

Author keywords

Concentration inequalities; Data dependent complexity; Empirical risk minimization; Generalization bounds; Isomorphic coordinate projections; Statistical learning theory

Indexed keywords

COMPUTATIONAL COMPLEXITY; FUNCTIONS; LEARNING ALGORITHMS; MATHEMATICAL MODELS; PROBABILITY; THEOREM PROVING; ALGORITHMS; ERRORS;

CONCENTRATION INEQUALITIES; DATA-DEPENDENT COMPLEXITY; EMPIRICAL RISK MINIMIZATION; GENERALIZATION BOUNDS; ISOMORPHIC COORDINATE PROJECTIONS; STATISTICAL LEARNING THEORY; CONCENTRATION INEQUALITY; DATA DEPENDENT; GENERALIZATION BOUND;

LEARNING SYSTEMS; RISK PERCEPTION;

EID: 9444247653     PISSN: 03029743     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1007/978-3-540-27819-1_19     Document Type: Conference Paper

References (21)

1. P.L. Bartlett, S. Boucheron, G. Lugosi: Model selection and error estimation. Machine Learning 48, 85-113, 2002.
2. P.L. Bartlett, O. Bousquet, S. Mendelson: Local Rademacher Complexities. Submitted, 2002 (available at http://www.stat.berkeley.edu/~bartlett/ publications/recent-pubs.html).
3. P.L. Bartlett, M.I. Jordan, J.D. McAuliffe: Convexity, classification, and risk bounds. Tech. Rep. 638, Dept. of Stat., U.C. Berkeley, 2003.
4. P.L. Bartlett, S. Mendelson: Empirical minimization. Submitted, 2003 (available at http://axiom.anu.edu.au/~shahar).
5. S. Boucheron, G. Lugosi, P. Massart: Concentration inequalities using the entropy method. Ann. of Prob. 31, 1583-1614, 2003.
6. O. Bousquet: Concentration Inequalities and Empirical Processes Theory Applied to the Analysis of Learning Algorithms. PhD. Thesis, 2002.
7. T. Klein: Une inégalité de concentration gauche pour les processus empiriques. C. R. Math. Acad. Sci. Paris 334(6), 501-504, 2002.
8. V. Koltchinskii, Rademacher penalties and structural risk minimization. IEEE Trans. on Info. Th. 47(5), 1902-1914, 2001.
9. V. Koltchinskii: Local Rademacher Complexities and Oracle Inequalities in Risk Minimization. Tech. Rep., Univ. of New Mexico, August 2003.
10. V. Koltchinskii and D. Panchenko, Rademacher processes and bounding the risk of function learning. In E. Gine and D. Mason and J. Wellner (Eds.), High Dimensional Probability II, 443-459, 2000.
11. M. Ledoux: The concentration of measure phenomenon. Mathematical Surveys and Monographs, Vol 89, AMS, 2001.
12. W.S. Lee, P.L. Bartlett, R.C. Williamson: The Importance of Convexity in Learning with Squared Loss. IEEE Trans. on Info Th., 44(5), 1974-1980, 1998.
13. G. Lugosi and M. Wegkamp, Complexity regularisation via localized random penalties. Ann. of Stat., to appear, 2003.
14. P. Massart: About the constants in Talagrand's concentration inequality for empirical processes. Ann. of Prob., 28(2), 863-884, 2000.
15. P. Massart. Some applications of concentration inequalities to statistics. Ann. de la Faculté des Sciences de Toulouse, IX: 245-303, 2000.
16. S. Mendelson, Improving the sample complexity using global data. IEEE Trans. on Info. Th. 48(7), 1977-1991, 2002.
17. S. Mendelson: A few notes on Statistical Learning Theory. In Proc. of the Machine Learning Summer School, Canberra 2002, S. Mendelson and A. J. Smola (Eds.), LNCS 2600, Springer, 2003.
18. S. Mendelson, Rademacher averages and phase transitions in Glivenko-Cantelli classes. IEEE Transactions on Information Theory 48(1), 251-263, 2002.
19. E. Rio: Inégalités de concentration pour les processus empiriques de classes de parties. Probab. Theory Related Fields 119(2), 163-175, 2001.
20. M. Talagrand: New concentration inequalities in product spaces. Invent. Math., 126, 505-563, 1996.
21. M. Talagrand: Sharper bounds for Gaussian and empirical processes. Ann. of Prob., 22(1), 28-76, 1994.