中文
相关论文

相关论文: A Unified Framework for Uniform Signal Recovery in…

200 篇论文

Recent advances in quantized compressed sensing and high-dimensional estimation have shown that signal recovery is even feasible under strong non-linear distortions in the observation process. An important characteristic of associated…

信息论 · 计算机科学 2023-08-08 Martin Genzel , Alexander Stollenwerk

In this paper, we study the problem of signal estimation from noisy non-linear measurements when the unknown $n$-dimensional signal is in the range of an $L$-Lipschitz continuous generative model with bounded $k$-dimensional inputs. We make…

机器学习 · 统计学 2020-10-09 Zhaoqiang Liu , Jonathan Scarlett

One-bit compressed sensing (1bCS) is an extremely quantized signal acquisition method that has been proposed and studied rigorously in the past decade. In 1bCS, linear samples of a high dimensional signal are quantized to only one bit per…

信息论 · 计算机科学 2022-11-01 Namiko Matsumoto , Arya Mazumdar , Soumyabrata Pal

One-bit compressed sensing (1bCS) is an extreme-quantized signal acquisition method that has been intermittently studied in the past decade. In 1bCS, linear samples of a high dimensional signal are quantized to only one bit per sample (sign…

信息论 · 计算机科学 2021-09-15 Arya Mazumdar , Soumyabrata Pal

One-bit compressed sensing (1bCS) addresses the recovery of sparse signals from highly quantized measurements, retaining only the sign of each linear measurement. In the support recovery setting, the goal is to identify $\text{supp}(x)$,…

信息论 · 计算机科学 2026-04-14 Xiaxin Li , Arya Mazumdar

This paper studies quantized corrupted sensing where the measurements are contaminated by unknown corruption and then quantized by a dithered uniform quantizer. We establish uniform guarantees for Lasso that ensure the accurate recovery of…

信息论 · 计算机科学 2024-01-17 Junren Chen , Zhaoqiang Liu , Meng Ding , Michael K. Ng

The goal of compressed sensing is to estimate a vector from an underdetermined system of noisy linear measurements, by making use of prior knowledge on the structure of vectors in the relevant domain. For almost all results in this…

机器学习 · 统计学 2017-03-10 Ashish Bora , Ajil Jalal , Eric Price , Alexandros G. Dimakis

The goal of standard 1-bit compressive sensing is to accurately recover an unknown sparse vector from binary-valued measurements, each indicating the sign of a linear function of the vector. Motivated by recent advances in compressive…

机器学习 · 统计学 2020-06-23 Zhaoqiang Liu , Selwyn Gomes , Avtansh Tiwari , Jonathan Scarlett

This paper studies the problem of reconstructing sparse or compressible signals from compressed sensing measurements that have undergone nonuniform quantization. Previous approaches to this Quantized Compressed Sensing (QCS) problem based…

信息论 · 计算机科学 2013-05-17 L. Jacques , D. K. Hammond , M. J. Fadili

A {\em universal 1-bit compressive sensing (CS)} scheme consists of a measurement matrix $A$ such that all signals $x$ belonging to a particular class can be approximately recovered from $\textrm{sign}(Ax)$. 1-bit CS models extreme…

信息论 · 计算机科学 2022-05-19 Sidhant Bansal , Arnab Bhattacharyya , Anamay Chaturvedi , Jonathan Scarlett

While it is well known that the restricted isometry property (RIP) guarantees uniform sparse recovery from noisy linear measurements, uniform recovery of structured signals from nonlinear observations remains much less understood. This…

信息论 · 计算机科学 2026-04-23 Pedro Abdalla , Radu Balan , Junren Chen

We study the fundamental problem of learning an unknown object from data using a prescribed model class. We introduce a unified framework that accommodates objects in arbitrary Hilbert spaces, general (possibly vector-valued) random linear…

机器学习 · 计算机科学 2026-03-09 Ben Adcock , Juan M. Cardenas , Nick Dexter

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} =…

信息论 · 计算机科学 2021-11-02 Alireza Naderi , Yaniv Plan

We study the compressed sensing (CS) signal estimation problem where an input signal is measured via a linear matrix multiplication under additive noise. While this setup usually assumes sparsity or compressibility in the input signal…

信息论 · 计算机科学 2014-12-23 Junan Zhu , Dror Baron , Marco F. Duarte

A pre-trained generator has been frequently adopted in compressed sensing (CS) due to its ability to effectively estimate signals with the prior of NNs. In order to further refine the NN-based prior, we propose a framework that allows the…

机器学习 · 计算机科学 2020-11-03 Kyung-Su Kim , Jung Hyun Lee , Eunho Yang

Parallel acquisition systems are employed successfully in a variety of different sensing applications when a single sensor cannot provide enough measurements for a high-quality reconstruction. In this paper, we consider compressed sensing…

信息论 · 计算机科学 2023-08-31 Il Yong Chun , Ben Adcock

Compressive sensing (CS) has triggered enormous research activity since its first appearance. CS exploits the signal's sparsity or compressibility in a particular domain and integrates data compression and acquisition, thus allowing exact…

计算机视觉与模式识别 · 计算机科学 2015-06-16 Shmuel Friedland , Qun Li , Dan Schonfeld

In this paper, we propose a generalized expectation consistent signal recovery algorithm to estimate the signal $\mathbf{x}$ from the nonlinear measurements of a linear transform output $\mathbf{z}=\mathbf{A}\mathbf{x}$. This estimation…

信息论 · 计算机科学 2017-05-15 Hengtao He , Chao-Kai Wen , Shi Jin

In phase-only compressive sensing (PO-CS), our goal is to recover low-complexity signals (e.g., sparse signals, low-rank matrices) from the phase of complex linear measurements. While perfect recovery of signal direction in PO-CS was…

信息论 · 计算机科学 2023-07-10 Junren Chen , Michael K. Ng

One-bit compressed sensing (1bCS) is a method of signal acquisition under extreme measurement quantization that gives important insights on the limits of signal compression and analog-to-digital conversion. The setting is also equivalent to…

信息论 · 计算机科学 2021-05-12 Larkin Flodin , Venkata Gandikota , Arya Mazumdar
‹ 上一页 1 2 3 10 下一页 ›