# Auto-Unrolled Proximal Gradient Descent: An AutoML Approach to Interpretable Waveform Optimization

arXiv: https://arxiv.org/abs/2603.17478 · HTML: https://mlsanity.com/paper/2603.17478/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 16 references that are in the map.
- First posted on arXiv 18 Mar 2026.

## Builds on (most cited first, 7 of 7)

- [AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data](https://mlsanity.com/paper/2003.06505/) (2020)
- [Deep Unfolding for Communications Systems: A Survey and Some New Directions](https://mlsanity.com/paper/1906.05774/) (2019)
- [Iterative Algorithm Induced Deep-Unfolding Neural Networks: Precoding Design for Multiuser MIMO Systems](https://mlsanity.com/paper/2006.08099/) (2020)
- [Deep Learning for Physical-Layer 5G Wireless Techniques: Opportunities, Challenges and Solutions](https://mlsanity.com/paper/1904.09673/) (2019)
- [Between hard and soft thresholding: optimal iterative thresholding algorithms](https://mlsanity.com/paper/1804.08841/) (2018)
- [Deep Unfolding: Recent Developments, Theory, and Design Guidelines](https://mlsanity.com/paper/2512.03768/) (2025)
- [Deep Unfolded Fractional Optimization for Maximizing Robust Throughput in 6G Networks](https://mlsanity.com/paper/2602.06062/) (2026)

## Abstract (arXiv)

This study explores the combination of automated machine learning (AutoML) with model-based deep unfolding (DU) for optimizing wireless beamforming and waveforms. We convert the iterative proximal gradient descent (PGD) algorithm into a deep neural network, wherein the parameters of each layer are learned instead of being predetermined. Additionally, we enhance the architecture by incorporating a hybrid layer that performs a learnable linear gradient transformation prior to the proximal projection. By utilizing AutoGluon with a tree-structured parzen estimator (TPE) for hyperparameter optimization (HPO) across an expanded search space, which includes network depth, step-size initialization, optimizer, learning rate scheduler, layer type, and post-gradient activation, the proposed auto-unrolled PGD (Auto-PGD) achieves 98.8% of the spectral efficiency of a traditional 200-iteration PGD solver using only five unrolled layers, while requiring only 100 training samples. We also address a gradient normalization issue to ensure consistent performance during training and evaluation, and we illustrate per-layer sum-rate logging as a tool for transparency. These contributions highlight a notable reduction in the amount of training data and inference cost required, while maintaining high interpretability compared to conventional black-box architectures.