A General Deep Learning Framework for Wireless Resource Allocation under Discrete Constraints

2026-03-17

AI Summary

This work proposes a general deep learning framework to address key challenges in wireless resource allocation involving discrete variables—namely, vanishing gradients, difficulty in satisfying complex constraints, and the inability to generate non-SPSD (non-same-parameter-same-decision) solutions. The framework represents discrete variables via support sets, models their joint probability distribution, and leverages conditional probability decomposition with dynamic context embedding for efficient optimization. For the first time, it unifies the resolution of these three challenges through probabilistic modeling, naturally accommodating complex discrete constraints and yielding diverse, high-quality solutions. Evaluated on two canonical scenarios—cell-free user association with beamforming and mobile antenna placement with beamforming—the proposed method significantly outperforms existing baselines in both system performance and computational efficiency.

Technology Category

• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Search and Optimization: Mixed Discrete/Continuous Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

While deep learning (DL)-based methods have achieved remarkable success in continuous wireless resource allocation, efficient solutions for problems involving discrete variables remain challenging. This is primarily due to the zero-gradient issue in backpropagation, the difficulty of enforcing intricate constraints with discrete variables, and the inability in generating solutions with non-same-parameter-same-decision (non-SPSD) property. To address these challenges, this paper proposes a general DL framework by introducing the support set to represent the discrete variables. We model the elements of the support set as random variables and learn their joint probability distribution. By factorizing the joint probability as the product of conditional probabilities, each conditional probability is sequentially learned. This probabilistic modeling directly tackles all the aforementioned challenges of DL for handling discrete variables. By operating on probability distributions instead of hard binary decisions, the framework naturally avoids the zero-gradient issue. During the learning of the conditional probabilities, discrete constraints can be seamlessly enforced by masking out infeasible solutions. Moreover, with a dynamic context embedding that captures the evolving discrete solutions, the non-SPSD property is inherently provided by the proposed framework. We apply the proposed framework to two representative mixed-discrete wireless resource allocation problems: (a) joint user association and beamforming in cell-free systems, and (b) joint antenna positioning and beamforming in movable antenna-aided systems. Simulation results demonstrate that the proposed DL framework consistently outperforms existing baselines in terms of both system performance and computational efficiency.

Problem

• discrete constraints
• wireless resource allocation
• deep learning
• zero-gradient issue
• non-SPSD property

Innovation

• discrete resource allocation
• deep learning
• support set
• probabilistic modeling
• non-SPSD property