Adaptive Beam Alignment using Noisy Twenty Questions Estimation with Trained Questioner

2026-01-23

AI Summary

This work addresses the high latency inherent in conventional beam alignment for 6G systems, which stems from sequential scanning, and overcomes limitations of existing adaptive approaches that either rely on unrealistic idealized assumptions or employ black-box neural networks at the cost of interpretability. The paper introduces, for the first time, a trainable questioning mechanism into beam alignment, grounded in a noisy twenty questions estimation framework. By integrating weighted steering vector mapping with a lightweight multilayer perceptron, the authors devise an information-theoretic active querying strategy that operates without ideal assumptions while maintaining both interpretability and computational efficiency. Simulations demonstrate that the proposed algorithm consistently outperforms current benchmarks in terms of alignment accuracy and sample efficiency.

Technology Category

• Machine Learning: Active Learning
• Search and Optimization: Sampling/Simulation-based Search
• Intelligent Robots: State Estimation

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

The 6G communication systems use mmWave and MIMO technologies to achieve wide bandwidth and high throughout, leading to indispensable need for beam alignment to overcome severe signal attenuation. Traditional sector-search-based beam alignment algorithms rely on sequential sampling to identify the best sector, resulting in a significant latency burden on 6G communication systems. Recently proposed adaptive beam alignment algorithms based on the active learning framework address the problem, aiming to identify the optimal sector with the fewest possible samples under an identical sector partition. Nevertheless, these algorithms either lack feasibility (Chiu, Ronquillo and Javidi, JSAC 2019) due to ideal assumptions or lack interpretability (Sohrabi, Chen and Yu, JSAC 2021) due to the use of end-to-end black-box neural networks. To avoid ideal assumptions and maintain interpretability, we address all above problems by proposing an adaptive beam alignment algorithm using the framework of noisy twenty questions estimation with a trained questioner. Specifically, we use two methods for training the questioner to eliminate reliance on ideal assumptions. The first method maps queries of twenty questions estimation to beamforming vectors via weighted summation of steering vectors, as an initial attempt to address the feasibility problem encountered in prior pioneering study by Chiu, Ronquillo and Javidi (JSAC 2019). The second method uses multi-layer fully connected neural networks to achieve improved performance while only employing them to train the questioner, which can effectively mitigate the interpretability issues in prior study by Sohrabi, Chen and Yu (JSAC 2021). Furthermore, we provide numerical simulations to illustrate the effectiveness of our proposed adaptive beam alignment algorithms and demonstrate that our algorithms outperform all benchmark algorithms.

Problem

• beam alignment
• 6G communication
• mmWave
• MIMO
• adaptive algorithm

Innovation

• adaptive beam alignment
• noisy twenty questions
• trained questioner
• interpretable neural networks
• mmWave MIMO