# Enabling Large Intelligent Surfaces with Compressive Sensing and Deep Learning

arXiv: https://arxiv.org/abs/1904.10136 · HTML: https://mlsanity.com/paper/1904.10136/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Apr 2019.

## Built on by (most cited first, 20 of 20)

- [Pervasive Machine Learning for Smart Radio Environments Enabled by Reconfigurable Intelligent Surfaces](https://mlsanity.com/paper/2205.03793/) (2022)
- [Multi-hop RIS-Empowered Terahertz Communications: A DRL-based Hybrid Beamforming Design](https://mlsanity.com/paper/2101.09137/) (2021)
- [Time-Varying Channel Prediction for RIS-Assisted MU-MISO Networks via Deep Learning](https://mlsanity.com/paper/2111.04971/) (2021)
- [Deep Learning-Based Rate-Splitting Multiple Access for Reconfigurable Intelligent Surface-Aided Tera-Hertz Massive MIMO](https://mlsanity.com/paper/2209.08456/) (2022)
- [A Robust Deep Learning-Based Beamforming Design for RIS-assisted Multiuser MISO Communications with Practical Constraints](https://mlsanity.com/paper/2111.06555/) (2021)
- [Autoencoder-based Communications with Reconfigurable Intelligent Surfaces](https://mlsanity.com/paper/2112.04441/) (2021)
- [Graph Attention Networks for Channel Estimation in RIS-assisted Satellite IoT Communications](https://mlsanity.com/paper/2104.00735/) (2021)
- [Channel Estimation and Hybrid Architectures for RIS-Assisted Communications](https://mlsanity.com/paper/2104.07115/) (2021)
- [Unsupervised Learning-Based Joint Resource Allocation and Beamforming Design for RIS-Assisted MISO-OFDMA Systems](https://mlsanity.com/paper/2506.22448/) (2025)
- [Wireless Dataset Similarity: Measuring Distances in Supervised and Unsupervised Machine Learning](https://mlsanity.com/paper/2601.01023/) (2026)
- [Making Intelligent Reflecting Surfaces More Intelligent: A Roadmap Through Reservoir Computing](https://mlsanity.com/paper/2102.03688/) (2021)
- [Covert Communications via Adversarial Machine Learning and Reconfigurable Intelligent Surfaces](https://mlsanity.com/paper/2112.11414/) (2021)
- [Reconfigurable Intelligent Surface Enabled Spatial Multiplexing with Fully Convolutional Network](https://mlsanity.com/paper/2201.02834/) (2022)
- [Machine Learning for Metasurfaces Design and Their Applications](https://mlsanity.com/paper/2211.01296/) (2022)
- [Deep Reinforcement Learning for IRS Phase Shift Design in Spatiotemporally Correlated Environments](https://mlsanity.com/paper/2211.09726/) (2022)
- [Revolutionizing Wireless Networks with Federated Learning: A Comprehensive Review](https://mlsanity.com/paper/2308.04404/) (2023)
- [Explainable Adversarial Learning Framework on Physical Layer Secret Keys Combating Malicious Reconfigurable Intelligent Surface](https://mlsanity.com/paper/2402.06663/) (2024)
- [Learning to Reflect: Hierarchical Multi-Agent Reinforcement Learning for CSI-Free mmWave Beam-Focusing](https://mlsanity.com/paper/2603.07370/) (2026)
- [Learning to Focus: CSI-Free Hierarchical MARL for Reconfigurable Reflectors](https://mlsanity.com/paper/2604.05165/) (2026)
- [A 3GPP-Compliant Benchmark Dataset for RIS-Aided Beyond 5G Networks](https://mlsanity.com/paper/2609.39058/) (2026)

## Abstract (arXiv)

Employing large intelligent surfaces (LISs) is a promising solution for improving the coverage and rate of future wireless systems. These surfaces comprise a massive number of nearly-passive elements that interact with the incident signals, for example by reflecting them, in a smart way that improves the wireless system performance. Prior work focused on the design of the LIS reflection matrices assuming full knowledge of the channels. Estimating these channels at the LIS, however, is a key challenging problem, and is associated with large training overhead given the massive number of LIS elements. This paper proposes efficient solutions for these problems by leveraging tools from compressive sensing and deep learning. First, a novel LIS architecture based on sparse channel sensors is proposed. In this architecture, all the LIS elements are passive except for a few elements that are active (connected to the baseband of the LIS controller). We then develop two solutions that design the LIS reflection matrices with negligible training overhead. In the first approach, we leverage compressive sensing tools to construct the channels at all the LIS elements from the channels seen only at the active elements. These full channels can then be used to design the LIS reflection matrices with no training overhead. In the second approach, we develop a deep learning based solution where the LIS learns how to optimally interact with the incident signal given the channels at the active elements, which represent the current state of the environment and transmitter/receiver locations. We show that the achievable rates of the proposed compressive sensing and deep learning solutions approach the upper bound, that assumes perfect channel knowledge, with negligible training overhead and with less than 1% of the elements being active.