Forward stagewise regression and the monotone lasso Export

@article{citeulike:3404025, abstract = {We consider the least angle regression and forward stagewise algorithms for solving penalized least squares regression problems. In Efron et al. (2004) it is proven that the least angle regression algorithm, with a small modification, solves the lasso (L1 constrained) regression problem. Here we give an analogous result for incremental forward stagewise regression, showing that it fits a monotone version of the lasso. We also study a condition under which the coefficient paths of the lasso are monotone, and hence the different algorithms all coincide. Finally, we compare the lasso and forward stagewise procedures in a simulation study involving a large number of correlated predictors.}, author = {Hastie, Trevor and Taylor, Jonathan and Tibshirani, Robert and Walther, Guenther}, citeulike-article-id = {3404025}, citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.62.480}, journal = {Electronic Journal of Statistics}, keywords = {feature, linear, regression, selection, variable}, posted-at = {2008-10-14 11:58:54}, priority = {4}, title = {Forward stagewise regression and the monotone lasso}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.62.480}, volume = {1}, year = {2007} }

TY - JOUR ID - citeulike:3404025 L3 - citeulike-article-id:3404025 N2 - We consider the least angle regression and forward stagewise algorithms for solving penalized least squares regression problems. In Efron et al. (2004) it is proven that the least angle regression algorithm, with a small modification, solves the lasso (L1 constrained) regression problem. Here we give an analogous result for incremental forward stagewise regression, showing that it fits a monotone version of the lasso. We also study a condition under which the coefficient paths of the lasso are monotone, and hence the different algorithms all coincide. Finally, we compare the lasso and forward stagewise procedures in a simulation study involving a large number of correlated predictors. JF - Electronic Journal of Statistics TI - Forward stagewise regression and the monotone lasso VL - 1 KW - feature KW - linear KW - regression KW - selection KW - variable AU - Hastie, Trevor AU - Taylor, Jonathan AU - Tibshirani, Robert AU - Walther, Guenther PY - 2007/// UR - http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.62.480 ER -