Algorithm Unrolling

Ask about this topic

Overview

Algorithm unrolling studies how to convert iterative solvers, such as ISTA and ADMM, into finite neural networks whose steps or regularizers can be learned from data. It is used in inverse problems including MRI, deblurring, compressive sensing, and spectral imaging, as well as constrained optimization and wireless resource allocation. Common approaches combine learned updates with physics-based measurement consistency, explicit constraints, or structured priors; scalable differentiation and warm-starting help train these models. A central tension is how to gain accuracy and speed from learned components while retaining convergence guarantees, interpretability, and reliable behavior beyond the training data.

Latest papers

CardsList

17 papers0 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

  1. Compact Snapshot Spectral Imaging with Calibration-Free Aperture Diffraction

    Aug 29, 2026Tao Lv, Quan Yuan, Shiqiao Li +5Hyperspectral ImagingComputational Imaging

    Nanjing University, Nanjing, 210023, China

  2. UMPIRE-Net: Unrolled Magnitude-Phase Regularization Network for Accelerated MRI

    Aug 14, 2026Mahdi Saberi, Toygan Kiliç, Mehmet AkçakayaAccelerated MRI ReconstructionPhysics-Informed ML

    Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA · Center for Magnetic Resonance Research, University of Minnesota, Minneapolis, MN, USA

  3. NanoMorph-3D: An End-to-End Physics-Driven Unrolling Framework for Nanomaterial Reconstruction

    Aug 4, 2026Beiyuan Zhang, Hesong Li, Ziqi Wu +23D ReconstructionAlgorithm Unrolling

    Beijing Institute of Technology Beijing, China

  4. Integrated Forward-Inverse Network for Lensless Image Reconstruction

    Jul 6, 2026Donggeon Bae, Jaewoo Jung, Yong Guk Kang +6Image ReconstructionComputational Imaging

    Department of Mechanical Engineering, Seoul National University, Republic of Korea · School of Mechanical and Aerospace Engineering/SNU-IAMD, Seoul National University, Republic of Korea · Department of Electrical and Electronic Engineering, Yonsei University, Republic of Korea +1

  5. Leveraging Phase Information to Boost Unrolled Network Learning for Image Deblurring

    Jun 30, 2026Samira Malek, Haichuan Zhang, Chul Lee +1Image DeblurringFrequency-Domain Image Processing

    Pennsylvania State University, University Park, PA 16802, USA · Dongguk University, Seoul 04620, South Korea

  6. Scalable Deep Unfolding of Conic Optimizers

    Jun 11, 2026Alex Oshin, Rahul Vodeb Ghosh, Evangelos A. TheodorouSemidefinite ProgrammingImplicit Differentiation

    Georgia Institute of Technology

  7. Structure-Preserving Correction Learning for Sparse Bayesian Inference in Brain Source Imaging

    Jun 5, 2026Marco Morik, Xiao Ruiting, Shinichi Nakajima +2ElectroencephalographyBayesian Inverse Problems

    Berlin Institute for the Foundations of Learning and Data (BIFOLD), Germany · Technische Universität Berlin, Germany · RIKEN Center for Advanced Intelligence Project (AIP), Japan +2

  8. DIFFRACT: Neuralized Utility Maximization for Wireless Networks by Differentiable Programming

    Jun 5, 2026Chee Wei Tan, Siya ChenAlgorithm UnrollingWireless Resource Allocation

    Nanyang Technological University, Singapore, Nanyang Ave., Singapore · Department of Computer Science, City University of Hong Kong, Hong Kong

  9. Physics-Aware Linearized ADMM and Its Unrolling

    Jun 1, 2026Satoshi Takabe, Shunta Arai, Tadashi WadayamaAlternating Direction Method of MultipliersAlgorithm 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

  10. Block-Wise Differentiable Sinkhorn Attention: Tail-Refinement Gradients with a Gap-Aware Dustbin Bridge

    Apr 28, 2026Dylan FordeAutomatic DifferentiationTransformer Attention

    Independent Researcher

  11. HUANet: Hard-Constrained Unrolled ADMM for Constrained Convex Optimization

    Apr 14, 2026Trinh Tran, Binh Nguyen, Truong X. NghiemLearning to OptimizeAlternating Direction Method of Multipliers

    Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL 32816, USA

  12. Compressive sensing inspired self-supervised single-pixel imaging

    Mar 31, 2026Jijun Lu, Yifan Chen, Libang Chen +5Image ReconstructionComputational Imaging

    Institute of Artificial Intelligence (TeleAI), China Telecom, China · School of Integrated Circuits, Shanghai Jiao Tong University, Shanghai, China · College of Future Information Technology, Fudan University, Shanghai, China +3

  13. Machine Learning-Assisted High-Dimensional Matrix Estimation

    Mar 30, 2026Wan Tian, Hui Yang, Zhouhui Lian +2Learning to OptimizeAlternating Direction Method of Multipliers

    Advanced Institute of Information Technology, Peking University · Wangxuan Institute of Computer Technology, Peking University, China, 100871 · Guanghua School of Management, Peking University, Beijing, China, 100871 +3

  14. Understanding the Curse of Unrolling

    Feb 23, 2026Sheheryar Mehmood, Florian Knoll, Peter OchsAlgorithm UnrollingDifferentiable Optimization

    Saarland University, Saarbrücken, Germany · Friedrich-Alexander University, Erlangen, Germany

  15. Learning to Control: The iUzawa-Net for Nonsmooth Optimal Control of Linear PDEs

    Feb 12, 2026Yongcun Song, Xiaoming Yuan, Hangrui Yue +1Optimal ControlConstrained Optimization

    Division of Mathematical Sciences, School of Physical and Mathematical Sciences, Nanyang Technological University, 21 Nanyang Link, 637371, Singapore. · Department of Mathematics, The University of Hong Kong, Pok Fu Lam, Hong Kong SAR, China. · School of Mathematical Sciences, Nankai University, Tianjin 300071, China.

  16. Learned iterative networks: An operator learning perspective

    Dec 9, 2025Andreas Hauptmann, Ozan ÖktemImage ReconstructionComputational Imaging

    Research Unit of Mathematical Sciences, University of Oulu, Finland · Department of Computer Science, University College London, United Kingdom · Department of Mathematics, KTH - Royal Institute of Technology, Sweden

  17. A Tunable Despeckling Neural Network Stabilized via Diffusion Equation

    Nov 24, 2024Yi Ran, Zhichang Guo, Jia Li +3Adversarial RobustnessAlgorithm Unrolling

    School of Mathematics, Harbin Institute of Technology, 150001 Harbin, China · Helmholtz Imaging, Deutsches Elektronen-Synchrotron DESY, 22607 Hamburg, Germany · Fachbereich Mathematik, Universität Hamburg, 20146 Hamburg, Germany