.png){kind=icon}
返回
Compressive phase retrieval: Optimal sample complexity with deep generative priors
.png){kind=icon}
OA
AI
DOI：10.1002/cpa.22155.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Advances in compressive sensing (CS) provided reconstruction algorithms of sparse signals from linear measurements with optimal sample complexity, but natural extensions of this methodology to nonlinear inverse problems have been met with potentially fundamental sample complexity bottlenecks. In particular, tractable algorithms for compressive phase retrieval with sparsity priors have not been able to achieve optimal sample complexity. This has created an open problem in compressive phase retrieval: under generic, phaseless linear measurements, are there tractable reconstruction algorithms that succeed with optimal sample complexity? Meanwhile, progress in machine learning has led to the development of new data-driven signal priors in the form of generative models, which can outperform sparsity priors with significantly fewer measurements. In this work, we resolve the open problem in compressive phase retrieval and demonstrate that generative priors can lead to a fundamental advance by permitting optimal sample complexity by a tractable algorithm. We additionally provide empirics showing that exploiting generative priors in phase retrieval can significantly outperform sparsity priors. These results provide support for generative priors as a new paradigm for signal recovery in a variety of contexts, both empirically and theoretically. The strengths of this paradigm are that (1) generative priors can represent some classes of natural signals more concisely than sparsity priors, (2) generative priors allow for direct optimization over the natural signal manifold, which is intractable under sparsity priors, and (3) the resulting non-convex optimization problems with generative priors can admit benign optimization landscapes at optimal sample complexity, perhaps surprisingly, even in cases of nonlinear measurements.
Keyword:
RESTRICTED ISOMETRY PROPERTY
STABLE SIGNAL RECOVERY
QUADRATIC MEASUREMENTS
IMAGE
ALGORITHMS
期刊
IF:
2.7
论文数:
1.5K
被引数:
1.1W
机构
引用论文
Electronic and optoelectronic properties of van der Waals heterostructure based on graphene-like GaN, blue phosphorene, SiC, and ZnO: A first principles study基于类石墨烯GaN，蓝色磷烯，SiC和ZnO的范德华异质结构的电子和光电性质: 第一性原理研究
.png){kind=icon}
PREAI
分享收藏Experimentelle Untersuchungen zur Ermüdung des Verbundes von Stahlbeton unter Querzug关于钢混凝土组合结构在横向拉力下的疲劳试验研究
PREAI
分享收藏Nutritional Limitation Sensitizes Mammalian Cells to GSK-3β Inhibitors and Leads to Growth Impairment营养限制使哺乳动物细胞对GSK-3β抑制剂更敏感，并导致生长受损
OAAI
OAAI分享收藏Graphene/Ionic Liquid Binary Electrode Material for High Performance Supercapacitor用于高性能超级电容器的石墨烯/离子液体二元电极材料
PREAI
分享收藏
查看更多内容