paper-with-me

Papers

Beyond Independent Measurements: General Compressed Sensing with GNN Application

2021-10-30 · NeurIPS Workshop Deep_Invers 2021 12 · Alireza Naderi, Yaniv Plan

We consider the problem of recovering a structured signal $\mathbf{x} \in \mathbb{R}^{n}$ from noisy linear observations $\mathbf{y} =\mathbf{M} \mathbf{x}+\mathbf{w}$. The measurement matrix is modeled as $\mathbf{M} = \mathbf{B}\mathbf{A}$, where $\mathbf{B} \in \mathbb{R}^{l \times m}$ is arbitrary and $\mathbf{A} \in \mathbb{R}^{m \times n}$ has independent sub-gaussian rows. By varying $\mathbf{B}$, and the sub-gaussian distribution of $\mathbf{A}$, this gives a family of measurement matrices which may have heavy tails, dependent rows and columns, and singular values with a large dynamic range. When the structure is given as a possibly non-convex cone $T \subset \mathbb{R}^{n}$, an approximate empirical risk minimizer is proven to be a robust estimator if the effective number of measurements is sufficient, even in the presence of a model mismatch. In classical compressed sensing with independent (sub-)gaussian measurements, one asks how many measurements are needed to recover $\mathbf{x}$? In our setting, however, the effective number of measurements depends on the properties of $\mathbf{B}$. We show that the effective rank of $\mathbf{B}$ may be used as a surrogate for the number of measurements, and if this exceeds the squared Gaussian mean width of $(T-T) \cap \mathbb{S}^{n-1}$, then accurate recovery is guaranteed. Furthermore, we examine the special case of generative priors in detail, that is when $\mathbf{x}$ lies close to $T = \mathrm{ran}(G)$ and $G: \mathbb{R}^k \rightarrow \mathbb{R}^n$ is a Generative Neural Network (GNN) with ReLU activation functions. Our work relies on a recent result in random matrix theory by Jeong, Li, Plan, and Yilmaz arXiv:2001.10631. .

📄 PDF Abstract BibTeX arXiv:2111.00327

Code (0)

등록된 구현이 없습니다.

Tasks

compressed sensing

Similar Papers 제목 키워드 기반

Near-Optimal Adaptive Compressed Sensing

2013-06-26 · Matthew L. Malloy, Robert D. Nowak

This paper proposes a simple adaptive sensing and group testing algorithm for sparse signal recovery. The algorithm, termed Compressive Adaptive Sense and Search (CASS), is shown to be near-optimal in that it succeeds at…

compressed sensing

Equivariant Imaging: Learning Beyond the Range Space

2021-03-26 · ICCV 2021 10 · Dongdong Chen, Julián Tachella, Mike E. Davies

In various imaging problems, we only have access to compressed measurements of the underlying signals, hindering most learning-based strategies which usually require pairs of signals and associated measurements for train…

Image Inpainting

Infinite dimensional generative sensing

2026-03-03 · Paolo Angella, Vito Paolo Pastore, Matteo Santacesaria arxiv

Deep generative models have become a standard for modeling priors for inverse problems, going beyond classical sparsity-based methods. However, existing theoretical guarantees are mostly confined to finite-dimensional ve…

A coherence parameter characterizing generative compressed sensing with Fourier measurements

2022-07-19 · Aaron Berk, Simone Brugiapaglia, Babhru Joshi, Yaniv Plan 외

In Bora et al. (2017), a mathematical framework was developed for compressed sensing guarantees in the setting where the measurement matrix is Gaussian and the signal structure is the range of a generative neural network…

compressed sensing

Auto-encoders for compressed sensing

2019-09-14 · NeurIPS Workshop Deep_Invers 2019 12 · Pei Peng, Shirin Jalali, Xin Yuan

Compressed sensing is about recovering a structured high-dimensional signal ${\bf x}\in R^n$ from its under-determined noisy linear measurements ${\bf y}\in R^m$, where $m\ll n$. While the vast majority of the literatur…

compressed sensing