Logistic Regression, AdaBoost and Bregman Distances Export

@inproceedings{citeulike:1364780, abstract = {. We give a unified account of boosting and logistic regression in which each learning problem is cast in terms of optimization of Bregman distances. The striking similarity of the two problems in this framework allows us to design and analyze algorithms for both simultaneously, and to easily adapt algorithms designed for one problem to the other. For both problems, we give new algorithms and explain their potential advantages over existing methods. These algorithms can be divided into two...}, author = {Collins, Michael and Schapire, Robert E. and Singer, Yoram}, booktitle = {Computational Learing Theory}, citeulike-article-id = {1364780}, citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.41.2618}, keywords = {bregman\_distance, nmf}, pages = {158--169}, posted-at = {2007-10-18 19:44:21}, priority = {2}, title = {Logistic Regression, AdaBoost and Bregman Distances}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.41.2618}, year = {2000} }

TY - CONF ID - citeulike:1364780 L3 - citeulike-article-id:1364780 N2 - . We give a unified account of boosting and logistic regression in which each learning problem is cast in terms of optimization of Bregman distances. The striking similarity of the two problems in this framework allows us to design and analyze algorithms for both simultaneously, and to easily adapt algorithms designed for one problem to the other. For both problems, we give new algorithms and explain their potential advantages over existing methods. These algorithms can be divided into two... EP - 169 TI - Logistic Regression, AdaBoost and Bregman Distances T2 - Computational Learing Theory SP - 158 KW - bregman_distance KW - nmf AU - Collins, Michael AU - Schapire, Robert AU - Singer, Yoram PY - 2000/// UR - http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.41.2618 ER -