# Pruning Unrolled Networks (PUN) at Initialization for MRI Reconstruction Improves Generalization

arXiv: https://arxiv.org/abs/2412.18668 · HTML: https://mlsanity.com/paper/2412.18668/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 30 references that are in the map.
- First posted on arXiv 24 Dec 2024.

## Builds on (most cited first, 16 of 16)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [fastMRI: An Open Dataset and Benchmarks for Accelerated MRI](https://mlsanity.com/paper/1811.08839/) (2018)
- [Deep Convolutional Neural Network for Inverse Problems in Imaging](https://mlsanity.com/paper/1611.03679/) (2016)
- [MoDL: Model Based Deep Learning Architecture for Inverse Problems](https://mlsanity.com/paper/1712.02862/) (2017)
- [A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations](https://mlsanity.com/paper/2308.06767/) (2023)
- [Task Transformer Network for Joint MRI Reconstruction and Super-Resolution](https://mlsanity.com/paper/2106.06742/) (2021)
- [DeepPET: A deep encoder-decoder network for directly solving the PET reconstruction inverse problem](https://mlsanity.com/paper/1804.07851/) (2018)
- [Test-Time Training Can Close the Natural Distribution Shift Performance Gap in Deep Learning Based Compressed Sensing](https://mlsanity.com/paper/2204.07204/) (2022)
- [Deep Equilibrium Learning of Explicit Regularizers for Imaging Inverse Problems](https://mlsanity.com/paper/2303.05386/) (2023)
- [Robustness of Deep Learning for Accelerated MRI: Benefits of Diverse Training Data](https://mlsanity.com/paper/2312.10271/) (2023)
- [Efficient Sum of Outer Products Dictionary Learning (SOUP-DIL) and Its Application to Inverse Problems](https://mlsanity.com/paper/1511.06333/) (2015)
- [Learning Sparsity-Promoting Regularizers using Bilevel Optimization](https://mlsanity.com/paper/2207.08939/) (2022)
- [SMUG: Towards robust MRI reconstruction by smoothed unrolling](https://mlsanity.com/paper/2303.12735/) (2023)
- [Optimal Eye Surgeon: Finding Image Priors through Sparse Generators at Initialization](https://mlsanity.com/paper/2406.05288/) (2024)

## Built on by (most cited first, 3 of 3)

- [Foundation Models for Medical Imaging: Status, Challenges, and Directions](https://mlsanity.com/paper/2602.15913/) (2026)
- [Beyond Sparsity: Weight Location and Network Context in Pruned MRI Reconstruction](https://mlsanity.com/paper/2609.31812/) (2026)
- [Awaken, Then Scale: Tiny Adaptation for MRI Reconstruction](https://mlsanity.com/paper/2609.31813/) (2026)

## Abstract (arXiv)

Deep learning methods are highly effective for many image reconstruction tasks. However, the performance of supervised learned models can degrade when applied to distinct experimental settings at test time or in the presence of distribution shifts. In this study, we demonstrate that pruning deep image reconstruction networks at training time can improve their robustness to distribution shifts. In particular, we consider unrolled reconstruction architectures for accelerated magnetic resonance imaging and introduce a method for pruning unrolled networks (PUN) at initialization. Our experiments demonstrate that when compared to traditional dense networks, PUN offers improved generalization across a variety of experimental settings and even slight performance gains on in-distribution data.