Compressed Sensing

Follow this topic Ask about this topic

Momentum

0 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 16

All topics

Full-Model Optimality for Tunable Linear Generative Priors in Compressed Sensing
Sep 2, 2026Zhaoming Li, Paul HandCompressed Sensing Model Selection
Department of Mathematics, Northeastern University, Boston, MA 02115, USA. · Department of Mathematics and Khoury College of Computer Sciences, Northeastern University, Boston, MA 02115, USA.
Learning the Mathematical Property for Designing Low Mutual Coherence Binary Sensing Matrices
Aug 13, 2026Rekha, Santosh Singh, S. K. NeogySparse Recovery Compressed Sensing
Department of Mathematics, Shiv Nadar Institution of Eminence, Delhi, India. · Centre for Research on Economics and Data Analysis (CREDA), Indian Statistical Institute, New Delhi, India.
Multilevel Graph Wavelet Compressed Sensing with Scale-Aware Neural Recovery
Jul 23, 2026Amirhossein Nouranizadeh, Sarang Rajendra Patil, Alan John Varghese +3Graph Signal Processing Sparse Recovery
Simplicial Technologies Inc., Toronto, ON, Canada · Department of Data Science, New Jersey Institute of Technology, Newark, NJ · School of Engineering, Brown University, Providence, RI +2
Quantum Compressed Sensing CT Reconstruction Algorithm Based on Penalized Weighted Least Squares and Guided Total Variation
Jul 12, 2026Yuwen Zhang, Yujie Liu, Ao Wang +4Sparse-View CT Reconstruction Quadratic Unconstrained Binary Optimization
Department of Medical Imaging Technology, Peking University Health Science Center, Beijing, China
Plug-and-Play Volumetric Reconstruction for Compressive Sensing Light-Sheet Microscopy
Jul 2, 2026Jianqing Jia, Yi Gong, Xinyuan Zhang +3Image Reconstruction Compressed Sensing
School of Data and Information Sciences, The University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA · Department of Mathematics, The University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA · Department of Bioengineering, The University of Texas at Dallas, Richardson, TX 75080, USA +1
An Integrated Hardware-Software Design for Low-Data Spatial Defect Detection in Robotic Visual Inspection with Hybrid Optoelectronic Neural Networks
Jun 24, 2026Chaoqing Tang, Jiaxuan Li, Huanze Zhuang +4Robotic Inspection Anomaly Localization
School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, 430074, China · China Belt and Road Joint Lab on Measurement and Control, Wuhan, 430074, China · School of Electric and Electrical Engineering, Chongqing University of Technology, Chongqing, 400054, China +1
Beyond Single Solution: Multi-Hypothesis Collaborative Deep Unfolding Network for Image Compressive Sensing
Jun 2, 2026Wenxue Cui, Hualin Li, Yuhang Qin +3Image Reconstruction Compressed Sensing
Harbin Institute of Technology, Harbin, China · Harbin Institute of Technology Suzhou Research Institute, Suzhou, China
Physics-Aware Linearized ADMM and Its Unrolling
Jun 1, 2026Satoshi Takabe, Shunta Arai, Tadashi WadayamaAlternating Direction Method of Multipliers Algorithm Unrolling
Department of Computer Science Institute of Science Tokyo Tokyo, Japan · Center for Advanced Intelligence Project RIKEN Tokyo, Japan · Department of Engineering Nagoya Institute of Technology Nagoya, Japan
Flow-Based Generative Modeling for Optimizing Sampling Policies in Compressed Sensing Applications
May 22, 2026Roman Pavelkin, Luis A. Zavala-Mondragon, Christiaan G. A. Viviers +1Flow Matching Image Reconstruction
Eindhoven University of Technology, Eindhoven
Deep Probabilistic Unfolding for Quantized Compressive Sensing
May 12, 2026Gang Qu, Ping Wang, Siming Zheng +1Compressed Sensing Deep Unfolding
Westlake University, School of Engineering, Hangzhou, Zhejiang, China · Vivo Mobile Communication Co., Ltd., Hangzhou, Zhejiang, China.
Active Learning for Conditional Generative Compressed Sensing
May 6, 2026Alexander DeLise, Nick DexterCompressed Sensing Conditional Generative Modeling
Department of Scientific Computing Department of Mathematics Florida State University · Department of Scientific Computing Florida State University
CSGuard: Toward Forgery-Resistant Watermarking in Diffusion Models via Compressed Sensing Constraint
May 2, 2026Jiewei Lai, Lan Zhang, Chen Tang +4Diffusion Model Watermarking Compressed Sensing
University of Science and Technology of China · Institute of Artificial Intelligence, Hefei Comprehensive National Science Center · Lenovo Research
Online CS-based SAR Edge-Mapping
Apr 21, 2026Conor Flynn, Radoslav Ivanov, Birsen YaziciRemote Sensing Compressed Sensing
Rensselaer Polytechnic Institute, Troy, New York, USA
Similarity of Neural Network Representations in Superposition
Mar 31, 2026Sunny Liu, Habon Issa, André Longon +4Feature Superposition Representational Similarity Analysis
Cold Spring Harbor Laboratory · UC San Diego · Anthropic +2
Compressed Sensing for Capability Localization in Large Language Models
Feb 11, 2026Anna Bair, Yixuan Even Xu, Mingjie Sun +1Attention Head Analysis LLM Interpretability
Carnegie Mellon University
Tunable Latent Generative Priors for Compressed Sensing and Inverse Problems
Date pendingSean Gunn, Jorio Cocola, Oliver De Candido +2Generative Modeling Compressed Sensing
Northeastern University · Harvard University · Technical University of Munich +1

Sep 2, 2026, stat.MLJ/K move · Enter open · S save

Full-Model Optimality for Tunable Linear Generative Priors in Compressed Sensing

Zhaoming Li, Paul Hand

Department of Mathematics, Northeastern University, Boston, MA 02115, USA. · Department of Mathematics and Khoury College of Computer Sciences, Northeastern University, Boston, MA 02115, USA.

Compressed Sensing Model Selection Generative Modeling

Open paper AskPDF arXiv

Generative models have been studied experimentally and theoretically as priors for inverse problems such as compressed sensing. Recent work by Gunn et al. studied the use of generative priors with tunable complexity, where a family of generative priors with varying complexity is maintained and a specific complexity can be selected at inversion time. They demonstrated that lower reconstruction errors can be experimentally attained for a variety of inverse problems by appropriately tuning the complexity of the generative prior. In the present paper, we establish theory for compressed sensing in the setting of a tunable family of linear generative priors naturally related through their singular value decompositions. We prove that in noiseless Gaussian compressed sensing, the full-dimensional linear prior attains the minimum expected reconstruction error over the entire family of linear priors. Thus, in this idealized linear noiseless setting, tuning to a lower-complexity prior does not improve the expected reconstruction error. This result is in contract to the behavior of denoising, where lower complexity priors attain lower reconstruction errors due to a standard bias-variance tradeoff. This result indicates that the experimental benefits of tunability in compressed sensing with neural network priors arises due to nonlinearities in the generative models.

Momentum

Related topics

Latest papers 16