We describe a fast method to eliminate features (variables) in l1 -penalized least-square regression (or LASSO) problems. The elimination of features leads to a potentially substantial reduction in running time, specially for large values of the penalty parameter. Our method is not heuristic: it only eliminates features that are guaranteed to be absent after solving the LASSO problem. The feature elimination step is easy to parallelize and can test each feature for elimination independently. Moreover, the computational effort of our method is negligible compared to that of solving the LASSO problem - roughly it is the same as single gradient step. Our method extends the scope of existing LASSO algorithms to treat larger data sets, previously out of their reach. We show how our method can be extended to general l1 -penalized convex problems and present preliminary results for the Sparse Support Vector Machine and Logistic Regression problems.
Safe Screening With Variational Inequalities and Its Application to LASSO
SAS Institute Inc.(赛仕软件研究所有限公司);Arizona State University(亚利桑那州立大学)
稀疏学习技术已经被常规地用于特征选择,因为所得到的模型通常具有少量的非零条目。安全筛选是一种提高计算效率的技术,它消除了对于正则化参数的某个值保证具有零系数的特征。安全筛选越来越受到关注,因为1)求解稀疏学习公式通常具有很高的计算成本,特别是当特征数量很大时,以及2)需要尝试几个正则化参数来选择合适的模型。在本文中,我们提出了一种方法称为“Sasvi”(安全筛选变分不等式)。Sasvi利用变分不等式为对偶问题提供了充分必要的最优性条件。Lasso筛选的几种现有方法可以被视为所提出的Sasvi的放松版本,因此Sasvi提供了更强的安全筛选规则。我们进一步研究了Sasvi for Lasso的单调性,基于此,可以为每个特征确定一个确定的移除正则化参数。合成和真实数据集上的实验结果表明,建议的Sasvi Lasso筛选的有效性。
Safe Distributionally Robust Feature Selection under Covariate Shift
Graduate School of Engineering, Nagoya University, Nagoya, Japan(名古屋大学工学研究科);Center for Advanced Intelligence Project, RIKEN, Tokyo, Japan(RIKEN高级智能项目)