TY - GEN
T1 - Convergence and consistency of recursive boosting
AU - Lozano, Aurélie C.
AU - Kulkarni, Sanjeev R.
PY - 2006
Y1 - 2006
N2 - We study the convergence and consistency of Boosting algorithms for classification. The standard method, as the sample size increases say from m to m +1, is to re-initialize the Boosting algorithm with an arbitrary prediction rule. In contrast to this "batch" approach, we propose a boosting procedure that is recursive in the sense that for sample size m + 1, the algorithm is re-started with the composite classifier that was obtained for sample size mata specific point, the linking point. We adopt the regularization technique of early stopping, which consists in stopping the procedure based on the 1-norm of the composite classifier. We prove that such recursive boosting methods achieve consistency provided certain stopping and linking points criteria are met. We show that these conditions can be satisfied for widely used loss functions.
AB - We study the convergence and consistency of Boosting algorithms for classification. The standard method, as the sample size increases say from m to m +1, is to re-initialize the Boosting algorithm with an arbitrary prediction rule. In contrast to this "batch" approach, we propose a boosting procedure that is recursive in the sense that for sample size m + 1, the algorithm is re-started with the composite classifier that was obtained for sample size mata specific point, the linking point. We adopt the regularization technique of early stopping, which consists in stopping the procedure based on the 1-norm of the composite classifier. We prove that such recursive boosting methods achieve consistency provided certain stopping and linking points criteria are met. We show that these conditions can be satisfied for widely used loss functions.
UR - http://www.scopus.com/inward/record.url?scp=39049152402&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=39049152402&partnerID=8YFLogxK
U2 - 10.1109/ISIT.2006.261938
DO - 10.1109/ISIT.2006.261938
M3 - Conference contribution
AN - SCOPUS:39049152402
SN - 1424405041
SN - 9781424405046
T3 - IEEE International Symposium on Information Theory - Proceedings
SP - 2185
EP - 2189
BT - Proceedings - 2006 IEEE International Symposium on Information Theory, ISIT 2006
T2 - 2006 IEEE International Symposium on Information Theory, ISIT 2006
Y2 - 9 July 2006 through 14 July 2006
ER -