arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1811.00577cs.LGeess.SPmath.OCstat.ML
收藏

泛函非线性稀疏模型

Functional Nonlinear Sparse Models

University of Pennsylvania(宾夕法尼亚大学);Weizmann Institute of Science(魏茨曼科学研究所)

Luiz F. O. Chamon, Yonina C. Eldar, Alejandro Ribeiro

摘要:

信号处理在本质上是连续的,通常是非线性的应用,如光谱估计,光学成像和超分辨率显微镜,其中稀疏性在获得最先进的结果中起着关键作用。处理这些问题的无穷维和非凸性通常涉及离散化和凸松弛,例如,使用原子规范。然而,网格失配和其他相干性问题通常导致稀疏信号的离散化版本不是稀疏的。即使它们是,使用凸松弛恢复稀疏解需要假设,可能很难满足在实践中。更重要的是,问题涉及非线性测量仍然是非凸的,即使放松稀疏性目标。我们解决这些问题,直接解决连续的,非线性问题铸造作为一个稀疏的功能优化程序。我们证明了当这些问题是非原子的,他们没有对偶间隙,因此可以有效地解决使用对偶和~(随机)凸优化方法。我们说明了这种方法的广泛应用,制定和解决问题的非线性谱估计和鲁棒分类。

英文摘要:

Signal processing is rich in inherently continuous and often nonlinear applications, such as spectral estimation, optical imaging, and super-resolution microscopy, in which sparsity plays a key role in obtaining state-of-the-art results. Coping with the infinite dimensionality and non-convexity of these problems typically involves discretization and convex relaxations, e.g., using atomic norms. Nevertheless, grid mismatch and other coherence issues often lead to discretized versions of sparse signals that are not sparse. Even if they are, recovering sparse solutions using convex relaxations requires assumptions that may be hard to meet in practice. What is more, problems involving nonlinear measurements remain non-convex even after relaxing the sparsity objective. We address these issues by directly tackling the continuous, nonlinear problem cast as a sparse functional optimization program. We prove that when these problems are non-atomic, they have no duality gap and can therefore be solved efficiently using duality and~(stochastic) convex optimization methods. We illustrate the wide range of applications of this approach by formulating and solving problems from nonlinear spectral estimation and robust classification.

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。

↑