arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.04813math.OC
收藏

精确稀疏Optimization的下界凸规划

Lower Bound Convex Programs for Exact Sparse Optimization

Jean-Philippe Chancelier, Michel De Lara, Ponts Paristech

摘要:

在Rd上的精确稀疏最优化问题(也称为稀疏约束问题)中,人们寻找具有很少非零分量的解。在本文中,我们考虑的问题,稀疏性是精确测量的非凸l0的的惩罚项(而不是由替代)或属于一个有限的联盟的子集的解决方案。由于稀疏约束的组合性质,即使最小化的标准是凸的,这样的问题通常也不显示凸性。在处理它们的最常见的方法中,人们用凸惩罚项代替稀疏约束,假设引起稀疏性。这样做,失去了原来的精确稀疏最优化问题,但获得凸性。然而,通过这样做,不清楚是否获得原始精确稀疏最优化问题的下界。在本文中,我们提出了另一种方法,我们失去了凸性,但我们在保持原来的精确稀疏优化配方,通过显示下界凸最小化程序。为此,我们引入合适的共轭,诱导一类新的单边线性耦合。因此,我们提出了一个系统的方法来设计规范和下界凸最小化程序的单位球。我们展示的范数家族包含了机器学习中使用的大多数稀疏诱导范数。因此,我们的方法为它们的使用提供了基础和解释。

英文摘要:

In exact sparse optimization problems on Rd (also known as sparsity constrained problems), one looks for solution that have few nonzero components. In this paper, we consider problems where sparsity is exactly measured either by the nonconvex l0 pseudonorm (and not by substitute penalty terms) or by the belonging of the solution to a finite union of subsets. Due to the combinatorial nature of the sparsity constraint, such problems do not generally display convexity properties, even if the criterion to minimize is convex. In the most common approach to tackle them, one replaces the sparsity constraint by a convex penalty term, supposed to induce sparsity. Thus doing, one loses the original exact sparse optimization problem, but gains convexity. However, by doing so, it is not clear that one obtains a lower bound of the original exact sparse optimization problem. In this paper, we propose another approach, where we lose convexity but where we gain at keeping the original exact sparse optimization formulation, by displaying lower bound convex minimization programs. For this purpose , we introduce suitable conjugacies, induced by a novel class of one-sided linear couplings. Thus equipped, we present a systematic way to design norms and lower bound convex minimization programs over their unit ball. The family of norms that we display encompasses most of the sparsity inducing norms used in machine learning. Therefore, our approach provides foundation and interpretation for their use.

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。

↑