# Physics-Informed Parametric Bandits for Beam Alignment in mmWave Communications

arXiv: https://arxiv.org/abs/2510.18299 · HTML: https://mlsanity.com/paper/2510.18299/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 48 references that are in the map.
- First posted on arXiv 21 Oct 2025.

## Builds on (most cited first, 12 of 12)

- [DeepMIMO: A Generic Deep Learning Dataset for Millimeter Wave and Massive MIMO Applications](https://mlsanity.com/paper/1902.06435/) (2019)
- [A Simple Approach for Non-stationary Linear Bandits](https://mlsanity.com/paper/2103.05324/) (2021)
- [DeepSense 6G: A Large-Scale Real-World Multi-Modal Sensing and Communication Dataset](https://mlsanity.com/paper/2211.09769/) (2022)
- [A Change-Detection based Framework for Piecewise-stationary Multi-Armed Bandit Problem](https://mlsanity.com/paper/1711.03539/) (2017)
- [Unimodal Bandits: Regret Lower Bounds and Optimal Algorithms](https://mlsanity.com/paper/1405.5096/) (2014)
- [Bandit Convex Optimisation](https://mlsanity.com/paper/2402.06535/) (2024)
- [Bandit Phase Retrieval](https://mlsanity.com/paper/2106.01660/) (2021)
- [Fast mmwave Beam Alignment via Correlated Bandit Learning](https://mlsanity.com/paper/1909.03313/) (2019)
- [Bandit Principal Component Analysis](https://mlsanity.com/paper/1902.03035/) (2019)
- [Near-Field Communications: A Tutorial Review](https://mlsanity.com/paper/2305.17751/) (2023)
- [Interference Constrained Beam Alignment for Time-Varying Channels via Kernelized Bandits](https://mlsanity.com/paper/2207.00908/) (2022)
- [Greedy Algorithm for Structured Bandits: A Sharp Characterization of Asymptotic Success / Failure](https://mlsanity.com/paper/2503.04010/) (2025)

## Abstract (arXiv)

In millimeter wave (mmWave) communications, beam alignment and tracking are crucial to combat the significant path loss. As scanning the entire directional space is inefficient, designing an efficient and robust method to identify the optimal beam directions is essential. Since traditional bandit algorithms require a long time horizon to converge under large beam spaces, many existing works propose efficient bandit algorithms for beam alignment by relying on unimodality or multimodality assumptions on the reward function's structure. However, such assumptions often do not hold (or cannot be strictly satisfied) in practice, which causes such algorithms to converge to choosing suboptimal beams. In this work, we propose two physics-informed bandit algorithms textitpretc and textitprgreedy that exploit the sparse multipath property of mmWave channels - a generic but realistic assumption - which is connected to the Phase Retrieval Bandit problem. Our algorithms treat the parameters of each path as black boxes and maintain optimal estimates of them based on sampled historical rewards. textitpretc starts with a random exploration phase and then commits to the optimal beam under the estimated reward function. textitprgreedy performs such estimation in an online manner and chooses the best beam under current estimates. Our algorithms can also be easily adapted to beam tracking in the mobile setting. Through experiments using both the synthetic DeepMIMO dataset and the real-world DeepSense6G dataset, we demonstrate that both algorithms outperform existing approaches in a wide range of scenarios across diverse channel environments, showing their generalizability and robustness.