Learning from dependent observations

Journal of Multivariate Analysis

Volumn 100, Issue 1, 2009, Pages 175-194

  Steinwart, Ingo ^a   Hush, Don ^a   Scovel, Clint ^a  

^a LOS ALAMOS NATIONAL LABORATORY   (United States)

Author keywords

62G08 (2000); 62H30 (1973); 62M45 (2000); 68Q32 (2000); 68T05 (1985); Classification; Consistency; Non stationary mixing process; primary; Regression; secondary; Support vector machine

Indexed keywords

EID: 55049121775     PISSN: 0047259X     EISSN: 10957243     Source Type: Journal    
DOI: 10.1016/j.jmva.2008.04.001     Document Type: Article

References (45)

1. Steinwart I. Support vector machines are universally consistent. J. Complexity 18 (2002) 768-791
2. Zhang T. Statistical behaviour and consistency of classification methods based on convex risk minimization. Ann. Statist. 32 (2004) 56-134
3. Steinwart I. Consistency of support vector machines and other regularized kernel machines. IEEE Trans. Inform. Theory 51 (2005) 128-142
4. Christmann A., and Steinwart I. Consistency and robustness of kernel based regression. Bernoulli 13 (2007) 799-819
5. Chen D.R., Wu Q., Ying Y.M., and Zhou D.X. Support vector machine soft margin classifiers: Error analysis. J. Mach. Learn. Res. 5 (2004) 1143-1175
6. Steinwart I., and Scovel C. Fast rates for support vector machines. Proceedings of the 18th Annual Conference on Learning Theory. COLT 2005 (2005), Springer 279-294
7. Blanchard G., Bousquet O., and Massart P. Statistical performance of support vector machines. Ann. Statist. 36 (2008) 489-531
8. Koltchinskii V., and Beznosova O. Exponential convergence rates in classification. Proceedings of the 18th Annual Conference on Learning Theory. COLT 2005 (2005), Springer 295-307
9. Steinwart I., and Scovel C. Fast rates for support vector machines using Gaussian kernels. Ann. Statist. 35 (2007) 575-607
10. Nobel A.B. Limits to classification and regression estimation from ergodic processes. Ann. Statist. 27 (1999) 262-273
11. Vidyasagar M. A Theory of Learning and Generalization: With Applications to Neural Networks and Control Systems. 2nd edition (2002), Springer, London
12. Irle A. On consistency in nonparametric estimation under mixing conditions. J. Multivariate Anal. 60 (1997) 123-147
13. Györfi L., Kohler M., Krzyżak A., and Walk H. A Distribution-Free Theory of Nonparametric Regression (2002), Springer, New York
14. Modha D.S., and Masry E. Memory-universal prediction of stationary random processes. IEEE Trans. Inform. Theory 44 (1998) 117-133
15. Meir R. Nonparametric time series prediction through adaptive model selection. Mach. Learn. 39 (2000) 5-34
16. Györfi L., Härdle W., Sarda P., and Vieu P. Nonparametric Curve Estimation from Time Series (1989), Springer, Berlin
17. Bosq D. Nonparametric Statistics for Stochastic Processes. 2nd edition (1998), Springer, New York
18. Gray R.M., and Kieffer J.C. Asymptotically mean stationary measures. Ann. Probab. 8 (1980) 962-973
19. Révész P. The Laws of Large Numbers (1968), Academic Press, New York
20. Krengel U. Ergodic Theorems (1985), de Gruyter, Berlin
21. Petersen K. Ergodic Theory. paperback edition (1989), Cambridge University Press
22. Doob J.L. Stochastic Processes (1953), Wiley, New York
23. Bhattacharya R., and Waymire E.C. Iterated random maps and some classes of markov processes. In: Shanbhag D.N., and Rao C.R. (Eds). Handbook of Statistics vol. 19 (2001), North-Holland 145-170
24. Norris J.R. Markov Chains (1997), Cambridge University Press
25. Aronszajn N. Theory of reproducing kernels. Trans. Amer. Math. Soc. 68 (1950) 337-404
26. Cristianini N., and Shawe-Taylor J. An Introduction to Support Vector Machines (2000), Cambridge University Press
27. Schölkopf B., and Smola A.J. Learning with Kernels (2002), MIT Press
28. Steinwart I., Hush D., and Scovel C. Function classes that approximate the Bayes risk. Proceedings of the 19th Annual Conference on Learning Theory. COLT 2006 (2006), Springer 79-93
29. Steinwart I. On the influence of the kernel on the consistency of support vector machines. J. Mach. Learn. Res. 2 (2001) 67-93
30. Devroye L., Györfi L., and Lugosi G. A Probabilistic Theory of Pattern Recognition (1996), Springer, New York
31. Bradley R.C. Basic properties of strong mixing conditions. A survey and some open questions. Probab. Surveys 2 (2005) 107-144
32. Bradley R.C., Bryc W., and Janson S. Remarks on the foundations of measures of dependence. In: Puri M.L., Vilaplana J.P., and Wertz W. (Eds). New Perspectives in Theoretical and Applied Statistics (1987), Wiley 421-437
33. Dehling H., and Philipp W. Almost sure invariance principles for weakly dependent vector-valued random variables. Ann. Probab. 10 (1982) 689-701
34. R.C. Bradley, Introduction to strong mixing conditions, volume 1, Technical Report, Department of Mathematics, Indiana University, Bloomington, Custom Publishing of I.U., Bloomington, 2005
35. Fan J., and Yao Q. Nonlinear Time Series (2003), Springer, New York
36. R.C. Bradley, Introduction to strong mixing conditions, volume 2, Technical Report, Department of Mathematics, Indiana University, Bloomington, Custom Publishing of I.U., Bloomington, 2005
37. R.C. Bradley, Introduction to strong mixing conditions, volume 3, Technical Report, Department of Mathematics, Indiana University, Bloomington, Custom Publishing of I.U., Bloomington, 2005
38. Zhengyan L., and Chuanrong L. Limit Theory for Mixing Dependent Random Variables (1996), Science Press and Kluwer, New York, Dordrecht
39. Bartlett P.L., Jordan M.I., and McAuliffe J.D. Convexity, classification, and risk bounds. J. Amer. Statist. Assoc. 101 (2006) 138-156
40. Steinwart I., Hush D., and Scovel C. A new concentration result for regularized risk minimizers. In: Giné E., Koltchinskii V., Li W., and Zinn J. (Eds). High Dimensional Probability IV. Lecture Notes-Monograph Series vol. 51 (2006), Institute of Mathematical Statistics, Beachwood, OH 260-275
41. Lozano A.C., Kulkarni S.R., and Schapire R.E. Convergence and consistency of regularized boosting algorithms with stationary β-mixing observations. In: Weiss Y., Schölkopf B., and Platt J. (Eds). Advances in Neural Information Processing Systems vol. 18 (2006), MIT Press, Cambridge, MA
42. Dunford N., and Schwartz J.T. Linear Operators, Part I: General Theory. Wiley Classics Library edition (1988), Wiley, New York
43. Bauer H. Measure and Integration Theory (2001), De Gruyter, Berlin
44. DeVito E., Rosasco L., Caponnetto A., Piana M., and Verri A. Some properties of regularized kernel methods. J. Mach. Learn. Res. 5 (2004) 1363-1390
45. Lindenstrauss J., and Tzafriri L. Classical Banach Spaces I (1977), Springer, Berlin