Learning to Optimize: Training Deep Neural Networks for Wireless Resource Management

Abstract

For the past couple of decades, numerical optimization has played a central role in addressing wireless resource management problems such as power control and beamformer design. However, optimization algorithms often entail considerable complexity, which creates a serious gap between theoretical design/analysis and real-time processing. To address this challenge, we propose a new learning-based approach. The key idea is to treat the input and output of a resource allocation algorithm as an unknown non-linear mapping and use a deep neural network (DNN) to approximate it. If the non-linear mapping can be learned accurately by a DNN of moderate size, then resource allocation can be done in almost real time -- since passing the input through a DNN only requires a small number of simple operations. In this work, we address both the thereotical and practical aspects of DNN-based algorithm approximation with applications to wireless resource management. We first pin down a class of optimization algorithms that are `learnable' in theory by a fully connected DNN. Then, we focus on DNN-based approximation to a popular power allocation algorithm named WMMSE (Shi {\it et al} 2011). We show that using a DNN to approximate WMMSE can be fairly accurate -- the approximation error $\epsilon$ depends mildly [in the order of $\log (1/\epsilon )$] on the numbers of neurons and layers of the DNN. On the implementation side, we use extensive numerical simulations to demonstrate that DNNs can achieve orders of magnitude speedup in computational time compared to state-of-the-art power allocation algorithms based on optimization.

Submitted to TSP

References in corpus (7)

• Optimal Linear Precoding Strategies for Wideband Non-Cooperative Systems based on Game Theory-Part I: Nash Equilibria
• Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures
• Why Deep Neural Networks for Function Approximation?
• Deep Learning Based MIMO Communications
• Detection Algorithms for Communication Systems Using Deep Learning
• Recurrent Neural Radio Anomaly Detection
• Signal Processing and Optimal Resource Allocation for the Interference Channel

Cited by in corpus (110)

• Deep Learning Enabled Semantic Communication Systems
• Edge Learning for B5G Networks with Distributed Signal Processing: Semantic Communication, Edge Computing, and Wireless Sensing
• Multi-Agent Deep Reinforcement Learning for Dynamic Power Allocation in Wireless Networks
• A Deep Learning Framework for Optimization of MISO Downlink Beamforming
• Optimal Wireless Resource Allocation with Random Edge Graph Neural Networks
• Spatial Deep Learning for Wireless Scheduling
• Learning Optimal Resource Allocations in Wireless Systems
• Real-time Power System State Estimation and Forecasting via Deep Neural Networks
• Enabling AI in Future Wireless Networks: A Data Life Cycle Perspective
• Rethinking WMMSE: Can Its Complexity Scale Linearly With the Number of BS Antennas?
• Learning-Based Downlink Power Allocation in Cell-Free Massive MIMO Systems
• Learned Conjugate Gradient Descent Network for Massive MIMO Detection
• Artificial Neural Networks-Based Machine Learning for Wireless Networks: A Tutorial
• A Globally Optimal Energy-Efficient Power Control Framework and its Efficient Implementation in Wireless Interference Networks
• Two Applications of Deep Learning in the Physical Layer of Communication Systems
• Applications and Techniques for Fast Machine Learning in Science
• Learning Decentralized Wireless Resource Allocations with Graph Neural Networks
• Deep Reinforcement Learning for Radio Resource Allocation and Management in Next Generation Heterogeneous Wireless Networks: A Survey
• Deep Learning Methods for Universal MISO Beamforming
• Learning to Branch: Accelerating Resource Allocation in Wireless Networks
• Binary MIMO Detection via Homotopy Optimization and Its Deep Adaptation
• Learning to Continuously Optimize Wireless Resource in a Dynamic Environment: A Bilevel Optimization Perspective
• Coordinated Sum-Rate Maximization in Multicell MU-MIMO with Deep Unrolling
• Application of Machine Learning in Wireless Networks: Key Techniques and Open Issues
• Reinforcement Learning Based Vehicle-cell Association Algorithm for Highly Mobile Millimeter Wave Communication
• Centralized and Distributed Power Allocation for Max-Min Fairness in Cell-Free Massive MIMO
• Machine Learning Methods for Management UAV Flocks -- a Survey
• Embedding Model Based Fast Meta Learning for Downlink Beamforming Adaptation
• A Tutorial on Ultra-Reliable and Low-Latency Communications in 6G: Integrating Domain Knowledge into Deep Learning
• Optimal Solutions for Joint Beamforming and Antenna Selection: From Branch and Bound to Graph Neural Imitation Learning
• A Learning Aided Flexible Gradient Descent Approach to MISO Beamforming
• HybNet: A Hybrid Deep Learning -- Matched Filter Approach for IoT Signal Detection
• Deep Learning Enabled Optimization of Downlink Beamforming Under Per-Antenna Power Constraints: Algorithms and Experimental Demonstration
• Spiking Neural Networks for Detecting Satellite-Based Internet-of-Things Signals
• DDPG-Driven Deep-Unfolding with Adaptive Depth for Channel Estimation with Sparse Bayesian Learning
• Meta-learning Based Beamforming Design for MISO Downlink
• Graph-based Algorithm Unfolding for Energy-aware Power Allocation in Wireless Networks
• Learning to Continuously Optimize Wireless Resource In Episodically Dynamic Environment
• Uncertainty Injection: A Deep Learning Method for Robust Optimization
• Highly accurate quantum optimization algorithm for CT image reconstructions based on sinogram patterns
• Model-Free Learning of Optimal Ergodic Policies in Wireless Systems
• A matrix-inverse-free implementation of the MU-MIMO WMMSE beamforming algorithm
• An Introduction to Deep Learning for the Physical Layer
• Two-Stage Stochastic Optimization via Primal-Dual Decomposition and Deep Unrolling
• Machine Learning-aided Design of Thinned Antenna Arrays for Optimized Network Level Performance
• Power Allocation in Multi-User Cellular Networks: Deep Reinforcement Learning Approaches
• Towards Unified AI Models for MU-MIMO Communications: A Tensor Equivariance Framework
• A Deep Learning-Based Approach for Cell Outage Compensation in NOMA Networks
• Deep Learning based Wireless Resource Allocation with Application to Vehicular Networks
• Deep Learning Based Resource Assignment for Wireless Networks
• Building Encoder and Decoder with Deep Neural Networks: On the Way to Reality
• Deep Reinforcement Learning Based Mode Selection and Resource Management for Green Fog Radio Access Networks
• A Graph Neural Network Approach for Scalable Wireless Power Control
• Deep unfolding of the weighted MMSE beamforming algorithm
• Deep Learning based Radio Resource Management in NOMA Networks: User Association, Subchannel and Power Allocation
• Deep Actor-Critic Learning for Distributed Power Control in Wireless Mobile Networks
• Deep Learning for Ultra-Reliable and Low-Latency Communications in 6G Networks
• Iterative Algorithm Induced Deep-Unfolding Neural Networks: Precoding Design for Multiuser MIMO Systems
• Enabling Simulation-Based Optimization Through Machine Learning: A Case Study on Antenna Design
• Decentralized Inference with Graph Neural Networks in Wireless Communication Systems
• Deep Learning for Radio Resource Allocation with Diverse Quality-of-Service Requirements in 5G
• An Attention-Aided Deep Learning Framework for Massive MIMO Channel Estimation
• LORM: Learning to Optimize for Resource Management in Wireless Networks with Few Training Samples
• Topology Aware Deep Learning for Wireless Network Optimization
• Semantic Communication Systems for Speech Transmission
• Scalable Power Control/Beamforming in Heterogeneous Wireless Networks with Graph Neural Networks
• Learning to Beamform in Heterogeneous Massive MIMO Networks
• Unsupervised Learning for Asynchronous Resource Allocation in Ad-hoc Wireless Networks
• Deep-Learning Based Linear Precoding for MIMO Channels with Finite-Alphabet Signaling
• Graph Neural Networks for Power Allocation in Wireless Networks with Full Duplex Nodes
• An Overview on the Application of Graph Neural Networks in Wireless Networks
• Power Allocation in Multi-user Cellular Networks With Deep Q Learning Approach
• Transfer Learning for Mixed-Integer Resource Allocation Problems in Wireless Networks
• Transfer Learning with Reconstruction Loss
• Deep Reinforcement Learning for Multi-Agent Power Control in Heterogeneous Networks
• Graph Neural Networks for Scalable Radio Resource Management: Architecture Design and Theoretical Analysis
• Resource Allocation Using Gradient Boosting Aided Deep Q-Network for IoT in C-RANs
• Accelerating Generalized Benders Decomposition for Wireless Resource Allocation
• Machine Learning for Geometrically-Consistent Angular Spread Function Estimation in Massive MIMO
• Algorithm Unrolling for Massive Access via Deep Neural Network with Theoretical Guarantee
• Optimizing Wireless Systems Using Unsupervised and Reinforced-Unsupervised Deep Learning
• A Novel Deep Neural Network Based Approach for Sparse Code Multiple Access
• Semantic Communications for Speech Signals
• Uncertainty Aware Deep Neural Network for Multistatic Localization with Application to Ultrasonic Structural Health Monitoring
• Two-Timescale End-to-End Learning for Channel Acquisition and Hybrid Precoding
• Accelerating Graph Neural Networks via Edge Pruning for Power Allocation in Wireless Networks
• Joint Deep Reinforcement Learning and Unfolding: Beam Selection and Precoding for mmWave Multiuser MIMO with Lens Arrays
• Application of End-to-End Deep Learning in Wireless Communications Systems
• Machine Learning for Heterogeneous Ultra-Dense Networks with Graphical Representations
• Artificial Intelligence for 5G Wireless Systems: Opportunities, Challenges, and Future Research Directions
• A Deep Learning Based Resource Allocator for Communication Networks with Dynamic User Utility Demands
• Sparse Array Beamformer Design for Active and Passive Sensing
• Learning to Optimize with Unsupervised Learning: Training Deep Neural Networks for URLLC
• Multicell Power Control under Rate Constraints with Deep Learning
• Semantic Communications for Speech Recognition
• Differentiable Projection for Constrained Deep Learning
• Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications
• Deep Learning for Wireless Coded Caching with Unknown and Time-Variant Content Popularity
• Cost-efficient and Skew-aware Data Scheduling for Incremental Learning in 5G Network
• Deep Learning Methods for Joint Optimization of Beamforming and Fronthaul Quantization in Cloud Radio Access Networks
• Sparse Array Capon Beamformer Design Availing Deep Learning
• Model-driven Learning for Generic MIMO Downlink Beamforming With Uplink Channel Information
• Learning to Optimize Under Constraints with Unsupervised Deep Neural Networks
• Exploiting Deep Learning for Secure Transmission in an Underlay Cognitive Radio Network
• An Adaptive Deep Learning Algorithm Based Autoencoder for Interference Channels
• Optimal WDM Power Allocation via Deep Learning for Radio on Free Space Optics Systems
• Learning Robust Beamforming for MISO Downlink Systems
• On Deep Learning for Radio Resource Management in A Non-stationary Radio Environment
• Resource Allocation via Graph Neural Networks in Free Space Optical Fronthaul Networks
• Learning-Based Massive Beamforming