Constant-Expansion Suffices for Compressed Sensing with Generative Priors
NIPS 2020, 2020.
In Appendix C, we provide a detailed explanation of why the Weight Distribution Condition arises and we give a sketch of the basic theory of global landscape analysis for compressed sensing with generative priors
Generative neural networks have been empirically found very promising in providing effective structural priors for compressed sensing, since they can be trained to span low-dimensional data manifolds in high-dimensional signal spaces. Despite the non-convexity of the resulting optimization problem, it has also been shown theoretically t...More
PPT (Upload PPT)