Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Automation and Machine Learning
  4. Vol 7, Issue 1, 2026

A Learnable Proximal Gradient Unrolling Network for Sparse Learning: A Mathematical Optimization–Driven Machine Learning Framework

Download as PDF

DOI: 10.23977/autml.2026.070105 | Downloads: 3 | Views: 24

Author(s)

Yinyi Wang 1, Tongtong Xu 1, Jialin Zhang 1

Affiliation(s)

1 School of Mathematics and Science, Hebei GEO University, Shijiazhuang, Hebei, China

Corresponding Author

Yinyi Wang

ABSTRACT

Sparse learning is a fundamental topic connecting mathematical optimization and machine learning, and it is widely applied in signal reconstruction, feature selection, and robust regression. However, classical iterative solvers for sparse models often require careful manual parameter tuning and may converge slowly under ill-conditioned data or noisy observations. To address these limitations, this study develops a Learnable Proximal Gradient Unrolling Network (LPG-Net) by transforming the iterations of proximal gradient descent into a trainable deep architecture. The proposed method starts from the Least Absolute Shrinkage and Selection Operator (LASSO) formulation and embeds the proximal operator of the ℓ1-regularizer into each network layer, while enabling data-driven adaptation of key algorithmic parameters such as step sizes and thresholding strengths across layers. In addition, a monotonicity-inspired regularization term is introduced to encourage stable descent behavior during training. Experiments on sparse regression and signal denoising tasks indicate that LPG-Net achieves more accurate sparse recovery and faster inference than traditional optimization baselines and standard neural predictors, while retaining strong interpretability due to its explicit connection to optimization updates. The framework provides a principled pathway for integrating mathematical optimization structures into machine learning models for sparse and noise-robust learning problems.

KEYWORDS

Sparse learning; mathematical optimization; machine learning; proximal gradient descent; algorithm unrolling; Least Absolute Shrinkage and Selection Operator (LASSO)

CITE THIS PAPER

Yinyi Wang, Tongtong Xu, Jialin Zhang. A Learnable Proximal Gradient Unrolling Network for Sparse Learning: A Mathematical Optimization–Driven Machine Learning Framework. Automation and Machine Learning (2026). Vol. 7, No. 1, 38-47. DOI: http://dx.doi.org/10.23977/autml.2026.070105.

REFERENCES

[1] Nir Shlezinger, Jay Whang, Yonina C. Eldar, Alexandros G. Dimakis, "Model-Based Deep Learning," Proceedings of the IEEE, vol. 111, no. 5, pp. 465–499, 2023, doi: 10.1109/JPROC.2023.3247480. 
[2] Gregory Ongie, Ajil Jalal, Christopher A. Metzler, Richard G. Baraniuk, Alexandros G. Dimakis, Rebecca Willett, "Deep Learning Techniques for Inverse Problems in Imaging," IEEE Journal on Selected Areas in Information Theory, vol. 1, no. 1, pp. 39–56, 2020, doi: 10.1109/JSAIT.2020.2991563.
[3] Vishal Monga, Yuelong Li, Yonina C. Eldar, "Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processing," IEEE Signal Processing Magazine, vol. 38, no. 2, pp. 18–44, 2021, doi: 10.1109/MSP.2020.3016905. 
[4] Ulugbek S. Kamilov, Charles A. Bouman, Gregery T. Buzzard, Brendt Wohlberg, "Plug-and-Play Methods for Integrating Physical and Learned Models in Computational Imaging: Theory, Algorithms, and Applications," IEEE Signal Processing Magazine, vol. 40, no. 1, pp. 85–97, 2023, doi: 10.1109/MSP.2022.3199595.
[5] Jean-Christophe Pesquet, Audrey Repetti, Matthieu Terris, Yves Wiaux, "Learning Maximally Monotone Operators for Image Recovery," SIAM Journal on Imaging Sciences, vol. 14, no. 3, pp. 1206–1237, 2021, doi: 10.1137/20M1387961. 
[6] Sebastian Lunz, Andreas Hauptmann, Tanja Tarvainen, Carola-Bibiane Schönlieb, Simon Arridge, "On Learned Operator Correction in Inverse Problems," SIAM Journal on Imaging Sciences, vol. 14, no. 1, pp. 92–127, 2021, doi: 10.1137/20M1338460.
[7] Samuel Hurault, Arthur Leclaire, Nicolas Papadakis, "Proximal Denoiser for Convergent Plug-and-Play Optimization with Nonconvex Regularization," in Proceedings of the 39th International Conference on Machine Learning (ICML), PMLR, 2022. Available: https://proceedings.mlr.press/v162/hurault22a/hurault22a.pdf 
[8] Samuel Hurault, Antonin Chambolle, Arthur Leclaire, Nicolas Papadakis, "Convergent Plug-and-Play with Proximal Denoiser and Unconstrained Regularization Parameter,” Journal of Mathematical Imaging and Vision, vol. 66, pp. 616–638, 2024, doi: 10.1007/s10851-024-01195-w.
[9] Mikael Le Pendu, Christine Guillemot, "Preconditioned Plug-and-Play ADMM with Locally Adjustable Denoiser for Image Restoration," SIAM Journal on Imaging Sciences, vol. 16, no. 1, pp. 393–422, 2023, doi: 10.1137/22M1504809.
[10] Alessandro Benfenati, "Plug and Play Splitting Techniques for Poisson Image Restoration," Journal of Mathematical Imaging and Vision, 2025, doi: 10.1007/s10851-025-01273-7.
[11] Shaik Basheeruddin Shah, Pradyumna Pradhan, Wei Pu, Rohan Randhi, Miguel R. D. Rodrigues, Yonina C. Eldar, "Optimization Guarantees of Unfolded ISTA and ADMM Networks With Smooth Soft-Thresholding," IEEE Transactions on Signal Processing, vol. 72, pp. 3272–3286, 2024, doi: 10.1109/TSP.2024.3412981. 
[12] Brent W. De Weerdt, Yonina C. Eldar, Nikolaos Deligiannis, "Deep Unfolding Transformers for Sparse Recovery of Video," IEEE Transactions on Signal Processing, vol. 72, pp. 1782–1796, 2024, doi: 10.1109/TSP.2024.3381749.
[13] Aniket Pramanik, M. Bridget Zimmerman, Mathews Jacob, “Memory-efficient model-based deep learning with convergence and robustness guarantees,” IEEE Transactions on Computational Imaging, vol. 9, pp. 260–275, 2023, doi: 10.1109/TCI.2023.3252268.
[14] Jan Christian Hauffen, Linh Kästner, Samim Ahmadi, Peter Jung, Giuseppe Caire, Mathias Ziegler, "Learned Block Iterative Shrinkage Thresholding Algorithm for Photothermal Super Resolution Imaging," Sensors, vol. 22, no. 15, Art. no. 5533, 2022, doi: 10.3390/s22155533.
[15] Brett R. Levac, Marius Arvinte, Jonathan I. Tamir, "Federated End-to-End Unrolled Models for Magnetic Resonance Image Reconstruction," Bioengineering, vol. 10, no. 3, Art. no. 364, 2023, doi: 10.3390/bioengineering10030364.
[16] Pierre Ablin, Thomas Moreau, Mathurin Massias, Alexandre Gramfort, "Learning Step Sizes for Unfolded Sparse Coding," in Advances in Neural Information Processing Systems (NeurIPS), vol. 32, pp. 13100–13110, 2019. (No DOI; available from the official NeurIPS archive.) Available: https://papers.neurips.cc/paper/9469-learning-step-sizes-for-unfolded-sparse-coding 
[17] Daisuke Ito, Satoshi Takabe, Tadashi Wadayama, "Trainable ISTA for Sparse Signal Recovery," IEEE Transactions on Signal Processing, vol. 67, no. 12, pp. 3113–3125, 2019, doi: 10.1109/TSP.2019.2912879. 
[18] Mark Borgerding, Philip Schniter, Sundeep Rangan, "AMP-Inspired Deep Networks for Sparse Linear Inverse Problems," IEEE Transactions on Signal Processing, vol. 65, no. 16, pp. 4293–4308, 2017, doi: 10.1109/TSP.2017.2708040.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 4876
Visits: 240239

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.