TY - GEN
T1 - Convergence and consistency of regularized Boosting algorithms with stationary β-mixing observations
AU - Lozano, Aurélie C.
AU - Kulkarni, Sanjeev R.
AU - Schapire, Robert E.
PY - 2005
Y1 - 2005
N2 - We study the statistical convergence and consistency of regularized Boosting methods, where the samples are not independent and identically distributed (i.i.d.) but come from empirical processes of stationary β-mixing sequences. Utilizing a technique that constructs a sequence of independent blocks close in distribution to the original samples, we prove the consistency of the composite classifiers resulting from a regularization achieved by restricting the 1-norm of the base classifiers' weights. When compared to the i.i.d. case, the nature of sampling manifests in the consistency result only through generalization of the original condition on the growth of the regularization parameter.
AB - We study the statistical convergence and consistency of regularized Boosting methods, where the samples are not independent and identically distributed (i.i.d.) but come from empirical processes of stationary β-mixing sequences. Utilizing a technique that constructs a sequence of independent blocks close in distribution to the original samples, we prove the consistency of the composite classifiers resulting from a regularization achieved by restricting the 1-norm of the base classifiers' weights. When compared to the i.i.d. case, the nature of sampling manifests in the consistency result only through generalization of the original condition on the growth of the regularization parameter.
UR - http://www.scopus.com/inward/record.url?scp=84864048173&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84864048173&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84864048173
SN - 9780262232531
T3 - Advances in Neural Information Processing Systems
SP - 819
EP - 826
BT - Advances in Neural Information Processing Systems 18 - Proceedings of the 2005 Conference
T2 - 2005 Annual Conference on Neural Information Processing Systems, NIPS 2005
Y2 - 5 December 2005 through 8 December 2005
ER -