A l -norm penalized orthogonal forward regression

Hong, Xia, Chen, Sheng, Guo, Yi and Gao, Junbin (2017) A l -norm penalized orthogonal forward regression. International Journal of Systems Science, 48 (10), 2195-2201. (doi:10.1080/00207721.2017.1311383).

Record type: Article

Abstract

A l1-norm penalised orthogonal forward regression (l1-POFR) algorithm is proposed based on the concept of leave-one-out mean square error (LOOMSE), by defining a new l1-norm penalised cost function in the constructed orthogonal space and associating each orthogonal basis with an individually tunable regularisation parameter. Due to orthogonality, the LOOMSE can be analytically computed without actually splitting the data-set, and moreover a closed form of the optimal regularisation parameter is derived by greedily minimising the LOOMSE incrementally. We also propose a simple formula for adaptively detecting and removing regressors to an inactive set so that the computational cost of the algorithm is significantly reduced. Examples are included to demonstrate the effectiveness of this new l1-POFR approach.

Text

l1-norm Penalized Orthogonal Forward Regression - Accepted Manuscript

Available under License University of Southampton Accepted Manuscript Licence.

Download (130kB)

Text

l1norm

Download (246kB)