# Deep Learning-based Compressive Beam Alignment in mmWave Vehicular Systems

arXiv: https://arxiv.org/abs/2103.00125 · HTML: https://mlsanity.com/paper/2103.00125/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 35 references that are in the map.
- First posted on arXiv 27 Feb 2021.

## Builds on (most cited first, 15 of 15)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Deep Learning in Neural Networks: An Overview](https://mlsanity.com/paper/1404.7828/) (2014)
- [Convex Optimization: Algorithms and Complexity](https://mlsanity.com/paper/1405.4980/) (2014)
- [A Deep Learning Approach to Structured Signal Recovery](https://mlsanity.com/paper/1508.04065/) (2015)
- [Convolutional Neural Network based Multiple-Rate Compressive Sensing for Massive MIMO CSI Feedback: Design, Simulation, and Analysis](https://mlsanity.com/paper/1906.06007/) (2019)
- [Learning to Invert: Signal Recovery via Deep Convolutional Networks](https://mlsanity.com/paper/1701.03891/) (2017)
- [Deep Learning for Direct Hybrid Precoding in Millimeter Wave Massive MIMO Systems](https://mlsanity.com/paper/1905.13212/) (2019)
- [DeepCodec: Adaptive Sensing and Recovery via Deep Convolutional Neural Networks](https://mlsanity.com/paper/1707.03386/) (2017)
- [Deep Signal Recovery with One-Bit Quantization](https://mlsanity.com/paper/1812.00797/) (2018)
- [Distributed Compressive Sensing: A Deep Learning Approach](https://mlsanity.com/paper/1508.04924/) (2015)
- [Site-specific online compressive beam codebook learning in mmWave vehicular communication](https://mlsanity.com/paper/2005.05485/) (2020)
- [Deep learning-based beam alignment in mmWave vehicular networks](https://mlsanity.com/paper/1910.11402/) (2019)
- [MmWave vehicle-to-infrastructure communication: Analysis of urban microcellular networks](https://mlsanity.com/paper/1702.08122/) (2017)
- [ConvCSNet: A Convolutional Compressive Sensing Framework Based on Deep Learning](https://mlsanity.com/paper/1801.10342/) (2018)
- [FALP: Fast beam alignment in mmWave systems with low-resolution phase shifters](https://mlsanity.com/paper/1902.05714/) (2019)

## Built on by (most cited first, 1 of 1)

- [Learning and Adaptation for Millimeter-Wave Beam Tracking and Training: a Dual Timescale Variational Framework](https://mlsanity.com/paper/2107.05466/) (2021)

## Abstract (arXiv)

Millimeter wave vehicular channels exhibit structure that can be exploited for beam alignment with fewer channel measurements compared to exhaustive beam search. With fixed layouts of roadside buildings and regular vehicular moving trajectory, the dominant path directions of channels will likely be among a subset of beam directions instead of distributing randomly over the whole beamspace. In this paper, we propose a deep learning-based technique to design a structured compressed sensing (CS) matrix that is well suited to the underlying channel distribution for mmWave vehicular beam alignment. The proposed approach leverages both sparsity and the particular spatial structure that appears in vehicular channels. We model the compressive channel acquisition by a two-dimensional (2D) convolutional layer followed by dropout. We design fully-connected layers to optimize channel acquisition and beam alignment. We incorporate the low-resolution phase shifter constraint during neural network training by using projected gradient descent for weight updates. Furthermore, we exploit channel spectral structure to optimize the power allocated for different subcarriers. Simulations indicate that our deep learning-based approach achieves better beam alignment than standard CS techniques which use random phase shift-based design. Numerical experiments also show that one single subcarrier is sufficient to provide necessary information for beam alignment.