arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2302.02548cs.LGcs.NAmath.NA
收藏

$\ell_0$ -极小化问题的学习树

Learning Trees of $\ell_0$-Minimization Problems

University of Central Florida(中佛罗里达大学)

G. Welper

摘要:

欠定线性系统极小稀疏解的计算问题一般是$NP$困难的。具有额外属性的子集可以允许有效的算法,最值得注意的是具有限制等距属性(RIP)的问题可以通过凸$\ell_1$最小化来解决。虽然这些课程非常成功,但它们忽略了许多实际应用。在本文中,我们考虑了适应性强的类,这些类在越来越困难的样本课程上训练后易于处理。该设置旨在作为人类数学家的候选模型,人类数学家可能无法立即解决任意证明,但在经过适当的课程培训后,可能在相对灵活的子类或专业领域取得成功。

英文摘要:

The problem of computing minimally sparse solutions of under-determined linear systems is $NP$ hard in general. Subsets with extra properties, may allow efficient algorithms, most notably problems with the restricted isometry property (RIP) can be solved by convex $\ell_1$-minimization. While these classes have been very successful, they leave out many practical applications. In this paper, we consider adaptable classes that are tractable after training on a curriculum of increasingly difficult samples. The setup is intended as a candidate model for a human mathematician, who may not be able to tackle an arbitrary proof right away, but may be successful in relatively flexible subclasses, or areas of expertise, after training on a suitable curriculum.

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。

↑