arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1206.4632cs.LGmath.OCstat.ML
收藏

l_1,p群Lasso的完全分析

A Complete Analysis of the l_1,p Group-Lasso

University of Basel(巴塞尔大学)

Julia Vogt, Volker Roth

摘要:

Group-Lasso是机器学习方法中用于联合正则化的著名工具。虽然l_{1,2}和l_{1,\infty}版本已经被详细研究,并且存在有效的算法,但是关于其他l_{1,p}变体仍然存在未决问题。我们刻画了l_{1,p} Group-Lasso对所有p-范数(1 <= p <= \infty)有解的条件,并给出了一个统一的有效集算法.对于所有的p-范数,一个高效的投影梯度算法。这种新算法使我们能够在多任务学习环境中比较Group-Lasso的许多变体的预测性能,其目的是并行解决通过Group-Lasso约束耦合的许多学习问题。我们对合成数据和两个真实数据集进行了大规模实验。根据不同范数的理论特征,我们观察到p在1.5和2之间的弱耦合范数始终优于p >> 2的强耦合范数。

英文摘要:

The Group-Lasso is a well-known tool for joint regularization in machine learning methods. While the l_{1,2} and the l_{1,\infty} version have been studied in detail and efficient algorithms exist, there are still open questions regarding other l_{1,p} variants. We characterize conditions for solutions of the l_{1,p} Group-Lasso for all p-norms with 1 <= p <= \infty, and we present a unified active set algorithm. For all p-norms, a highly efficient projected gradient algorithm is presented. This new algorithm enables us to compare the prediction performance of many variants of the Group-Lasso in a multi-task learning setting, where the aim is to solve many learning problems in parallel which are coupled via the Group-Lasso constraint. We conduct large-scale experiments on synthetic data and on two real-world data sets. In accordance with theoretical characterizations of the different norms we observe that the weak-coupling norms with p between 1.5 and 2 consistently outperform the strong-coupling norms with p >> 2.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑