# Beam-aware Kernelized Contextual Bandits for User Association and Beamforming in mmWave Vehicular Networks

arXiv: https://arxiv.org/abs/2603.19285 · HTML: https://mlsanity.com/paper/2603.19285/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 27 references that are in the map.
- First posted on arXiv 8 Mar 2026.

## Builds on (most cited first, 5 of 5)

- [Finite-Time Analysis of Kernelised Contextual Bandits](https://mlsanity.com/paper/1309.6869/) (2013)
- [Communication Efficient Distributed Learning for Kernelized Contextual Bandits](https://mlsanity.com/paper/2206.04835/) (2022)
- [Joint Channel Selection and Power Control in Infrastructureless Wireless Networks: A Multi-Player Multi-Armed Bandit Framework](https://mlsanity.com/paper/1407.5447/) (2014)
- [Contextual Bandits with Non-Stationary Correlated Rewards for User Association in MmWave Vehicular Networks](https://mlsanity.com/paper/2410.05785/) (2024)
- [Learning-Based User Association for MmWave Vehicular Networks With Kernelized Contextual Bandits](https://mlsanity.com/paper/2504.10959/) (2025)

## Abstract (arXiv)

Timely channel information is necessary for vehicles to determine both the serving base station (BS) and the beamforming vector, but frequent estimation of fast-fading mmWave channels incurs significant overhead. To address this challenge, we propose a Beam-aware Kernelized Contextual Upper Confidence Bound (BKC-UCB) algorithm that estimates instantaneous transmission rates without additional channel measurements by exploiting historical contexts such as vehicle location and velocity, together with past observed transmission rates. Specifically, BKC-UCB leverages kernel methods to capture the nonlinear relationship between context and transmission rate by mapping contexts into a reproducing kernel Hilbert space (RKHS), where linear learning becomes feasible. Rather than treating each beam as an independent arm, the beam index is embedded into the context, enabling BKC-UCB to exploit correlations among beams to accelerate convergence. Furthermore, an event-triggered information sharing mechanism is incorporated into BKC-UCB, enabling information exchange only when significant explorations are conducted to improve learning efficiency with limited communication overhead.