arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1012.1501cs.LGstat.ML
收藏

利用次模函数形成水平集

Shaping Level Sets with Submodular Functions

INRIA(法国国家信息与自动化研究所);Laboratoire d’Informatique de l’Ecole Normale Supérieure(巴黎高等师范学院计算机实验室)

Francis Bach

摘要:

我们考虑一类基于次模函数的稀疏诱导正则化项。虽然以前的工作主要集中在非减函数,我们探讨对称次模函数及其\lova扩展。我们证明了Lovasz扩展可以被看作是依赖于水平集的函数的凸包络(即,其基础预测器的对应分量大于给定常数的索引集合):这导致一类凸结构正则化项,其将先验知识强加于水平集,而不仅仅是基础预测器的支持。我们提供了一套统一的优化算法,如近似运算符和理论保证(允许的水平集和恢复条件)。通过选择特定的子模函数,我们给出了一个新的解释,已知的规范,如总变差,我们还定义了新的规范,特别是那些基于顺序统计与应用程序的聚类和离群值检测,并在嘈杂的削减图中的应用程序的变化点检测中存在离群值。

英文摘要:

We consider a class of sparsity-inducing regularization terms based on submodular functions. While previous work has focused on non-decreasing functions, we explore symmetric submodular functions and their \lova extensions. We show that the Lovasz extension may be seen as the convex envelope of a function that depends on level sets (i.e., the set of indices whose corresponding components of the underlying predictor are greater than a given constant): this leads to a class of convex structured regularization terms that impose prior knowledge on the level sets, and not only on the supports of the underlying predictors. We provide a unified set of optimization algorithms, such as proximal operators, and theoretical guarantees (allowed level sets and recovery conditions). By selecting specific submodular functions, we give a new interpretation to known norms, such as the total variation; we also define new norms, in particular ones that are based on order statistics with application to clustering and outlier detection, and on noisy cuts in graphs with application to change point detection in the presence of outliers.

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。

↑