Phase Retrieval Under a Generative Prior
July 11, 2018 Β· Declared Dead Β· π Neural Information Processing Systems
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Paul Hand, Oscar Leong, Vladislav Voroninski
arXiv ID
1807.04261
Category
cs.IT: Information Theory
Cross-listed
cs.LG,
math.OC,
math.PR
Citations
203
Venue
Neural Information Processing Systems
Last Checked
3 months ago
Abstract
The phase retrieval problem asks to recover a natural signal $y_0 \in \mathbb{R}^n$ from $m$ quadratic observations, where $m$ is to be minimized. As is common in many imaging problems, natural signals are considered sparse with respect to a known basis, and the generic sparsity prior is enforced via $\ell_1$ regularization. While successful in the realm of linear inverse problems, such $\ell_1$ methods have encountered possibly fundamental limitations, as no computationally efficient algorithm for phase retrieval of a $k$-sparse signal has been proven to succeed with fewer than $O(k^2\log n)$ generic measurements, exceeding the theoretical optimum of $O(k \log n)$. In this paper, we propose a novel framework for phase retrieval by 1) modeling natural signals as being in the range of a deep generative neural network $G : \mathbb{R}^k \rightarrow \mathbb{R}^n$ and 2) enforcing this prior directly by optimizing an empirical risk objective over the domain of the generator. Our formulation has provably favorable global geometry for gradient methods, as soon as $m = O(kd^2\log n)$, where $d$ is the depth of the network. Specifically, when suitable deterministic conditions on the generator and measurement matrix are met, we construct a descent direction for any point outside of a small neighborhood around the unique global minimizer and its negative multiple, and show that such conditions hold with high probability under Gaussian ensembles of multilayer fully-connected generator networks and measurement matrices. This formulation for structured phase retrieval thus has two advantages over sparsity based methods: 1) deep generative priors can more tightly represent natural signals and 2) information theoretically optimal sample complexity. We corroborate these results with experiments showing that exploiting generative models in phase retrieval tasks outperforms sparse phase retrieval methods.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β Information Theory
R.I.P.
π»
Ghosted
R.I.P.
π»
Ghosted
A Vision of 6G Wireless Systems: Applications, Trends, Technologies, and Open Research Problems
R.I.P.
π»
Ghosted
Towards Smart and Reconfigurable Environment: Intelligent Reflecting Surface Aided Wireless Network
π
π
The Cartographer
Wireless Communications with Unmanned Aerial Vehicles: Opportunities and Challenges
R.I.P.
π»
Ghosted
Reconfigurable Intelligent Surfaces for Energy Efficiency in Wireless Communication
π
π
The Cartographer
An Overview of Signal Processing Techniques for Millimeter Wave MIMO Systems
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Federated Learning: Strategies for Improving Communication Efficiency
R.I.P.
π»
Ghosted
In-Datacenter Performance Analysis of a Tensor Processing Unit
R.I.P.
π»
Ghosted
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
R.I.P.
π»
Ghosted