# HoloBeam: Learning Optimal Beamforming in Far-Field Holographic Metasurface Transceivers

arXiv: https://arxiv.org/abs/2401.05420 · HTML: https://mlsanity.com/paper/2401.05420/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 40 references that are in the map.
- First posted on arXiv 30 Dec 2023.

## Builds on (most cited first, 20 of 20)

- [On the Complexity of Best Arm Identification in Multi-Armed Bandit Models](https://mlsanity.com/paper/1407.4443/) (2014)
- [Tight (Lower) Bounds for the Fixed Budget Best Arm Identification Bandit Problem](https://mlsanity.com/paper/1605.09004/) (2016)
- [Intelligent Reflecting Surface Enhanced Wireless Network via Joint Active and Passive Beamforming](https://mlsanity.com/paper/1810.03961/) (2018)
- [Millimeter Wave Channel Modeling and Cellular Capacity Evaluation](https://mlsanity.com/paper/1312.4921/) (2013)
- [Holographic MIMO Surfaces for 6G Wireless Networks: Opportunities, Challenges, and Trends](https://mlsanity.com/paper/1911.12296/) (2019)
- [Fast mmwave Beam Alignment via Correlated Bandit Learning](https://mlsanity.com/paper/1909.03313/) (2019)
- [Terahertz Massive MIMO with Holographic Reconfigurable Intelligent Surfaces](https://mlsanity.com/paper/2009.10963/) (2020)
- [Beam Focusing for Near-Field Multi-User MIMO Communications](https://mlsanity.com/paper/2105.13087/) (2021)
- [Physics-based Modeling and Scalable Optimization of Large Intelligent Reflecting Surfaces](https://mlsanity.com/paper/2004.12957/) (2020)
- [Beam Training based on Dynamic Hierarchical Codebook for Millimeter Wave Massive MIMO](https://mlsanity.com/paper/1901.01425/) (2019)
- [Joint Beam Training and Positioning For Intelligent Reflecting Surfaces Assisted Millimeter Wave Communications](https://mlsanity.com/paper/2009.03536/) (2020)
- [Fast Beam Alignment via Pure Exploration in Multi-armed Bandits](https://mlsanity.com/paper/2210.12625/) (2022)
- [Path Loss in Reconfigurable Intelligent Surface-Enabled Channels](https://mlsanity.com/paper/1912.06759/) (2019)
- [Channel Modeling and Channel Estimation for Holographic Massive MIMO with Planar Arrays](https://mlsanity.com/paper/2108.04633/) (2021)
- [Holographic Metasurface Antennas for Uplink Massive MIMO Systems](https://mlsanity.com/paper/2108.12513/) (2021)
- [Parametric Channel Estimation for LoS Dominated Holographic Massive MIMO Systems](https://mlsanity.com/paper/2112.02874/) (2021)
- [Multi-Armed Bandit Dynamic Beam Zooming for mmWave Alignment and Tracking](https://mlsanity.com/paper/2209.02896/) (2022)
- [Learning Optimal Phase-Shifts of Holographic Metasurface Transceivers](https://mlsanity.com/paper/2301.03371/) (2022)
- [UB3: Best Beam Identification in Millimeter Wave Systems via Pure Exploration Unimodal Bandits](https://mlsanity.com/paper/2301.03456/) (2022)
- [A Tutorial on Holographic MIMO Communications--Part I: Channel Modeling and Channel Estimation](https://mlsanity.com/paper/2305.15728/) (2023)

## Abstract (arXiv)

Holographic Metasurface Transceivers (HMTs) are emerging as cost-effective substitutes to large antenna arrays for beamforming in Millimeter and TeraHertz wave communication. However, to achieve desired channel gains through beamforming in HMT, phase-shifts of a large number of elements need to be appropriately set, which is challenging. Also, these optimal phase-shifts depend on the location of the receivers, which could be unknown. In this work, we develop a learning algorithm using a it fixed-budget multi-armed bandit framework to beamform and maximize received signal strength at the receiver for far-field regions. Our algorithm, named Algo exploits the parametric form of channel gains of the beams, which can be expressed in terms of two it phase-shifting parameters. Even after parameterization, the problem is still challenging as phase-shifting parameters take continuous values. To overcome this, itHB works with the discrete values of phase-shifting parameters and exploits their unimodal relations with channel gains to learn the optimal values faster. We upper bound the probability of itHB incorrectly identifying the (discrete) optimal phase-shift parameters in terms of the number of pilots used in learning. We show that this probability decays exponentially with the number of pilot signals. We demonstrate that itHB outperforms state-of-the-art algorithms through extensive simulations.