• Corpus ID: 56517405

LORA: Learning to Optimize for Resource Allocation in Wireless Networks with Few Training Samples

  title={LORA: Learning to Optimize for Resource Allocation in Wireless Networks with Few Training Samples},
  author={Yifei Shen and Yuanming Shi and Jun Zhang and Khaled Ben Letaief},
Effective resource allocation plays a pivotal role for performance optimization in wireless networks. Unfortunately, typical resource allocation problems are mixed-integer nonlinear programming (MINLP) problems, which are NP-hard in general. Machine learning-based methods recently emerge as a disruptive way to obtain near-optimal performance for MINLP problems with affordable computational complexity. However, a key challenge is that these methods require huge amounts of training samples, which… 
Learning to Branch: Accelerating Resource Allocation in Wireless Networks
In imitation learning method, a good auxiliary prune policy can be learned in a supervised manner to speed up the most time-consuming branch process of the B&B algorithm and the proposed method can achieve good optimality and reduce computational complexity simultaneously.
Calibrated Learning for Online Distributed Power Allocation in Small-Cell Networks
A combined calibrated learning and bandit approach to online distributed power control in small cell networks operated under the same frequency bandwidth outperforms the benchmark scheme with limited amount of information exchange and rapidly approaches towards the optimal centralized solution.
$Q$ - TRANSFER: A Novel Framework for Efficient Deep Transfer Learning in Networking
In this paper, we propose a novel framework, namely Q-TRANSFER, to address the insufficiency problem of the actual training data sets in modern networking platforms in order to push the application
Bandwidth Optimization Of Wireless Networks Using Artificial Intelligence Technique - IRE Journals
From the results, the proposed WOA technique efficiently optimized the bandwidth allocated to users and showed bandwidth management of the small amount of bandwidth.
Hybrid Beamforming for 5G and Beyond Millimeter-Wave Systems: A Holistic View
This paper presents a holistic view on hybrid beamforming for 5G and beyond mm-wave systems, based on a new taxonomy for different hardware structures, and compares different proposals from three key aspects: hardware efficiency, computational efficiency and achievable spectral efficiency.


Learning Optimal Resource Allocations in Wireless Systems
DNNs are trained here with a model-free primal-dual method that simultaneously learns a DNN parameterization of the resource allocation policy and optimizes the primal and dual variables.
Deep Reinforcement Learning for Distributed Dynamic Power Allocation in Wireless Networks
This work indicates that deep reinforcement learning based radio resource management can be very fast and deliver highly competitive performance, especially in practical scenarios where the system model is inaccurate and CSI delay is non-negligible.
Spatial Deep Learning for Wireless Scheduling
It is shown that it is possible to bypass the channel estimation stage altogether and to use a deep neural network to produce a near optimal schedule based solely on geographic locations of the transmitters and receivers in the network.
Learning to Optimize: Training Deep Neural Networks for Interference Management
A new learning-based perspective is provided to treat the input and output of an SP algorithm as an unknown nonlinear mapping and use a deep neural network (DNN) to approximate it, which can be accurately approximated by a fully connected DNN.
Towards Optimal Power Control via Ensembling Deep Neural Networks
Simulation results show that for the standard symmetric $K$ -user Gaussian interference channel, the proposed methods can outperform state-of-the-art power control solutions under a variety of system configurations.
To obtain near-optimal solutions at affordable complexity, this paper proposes to approximate the branch-and-bound algorithm via machine learning, formulated as a sequential decision problem, followed by learning the oracle’s action via imitation learning.
Resource Allocation for Wireless Networks: Basics, Techniques, and Applications
Unique in its scope, timeliness, and innovative author insights, this invaluable work will help graduate students and researchers to understand the basics of wireless resource allocation whilst highlighting modern research topics, and will help industrial engineers to improve system optimization.
Group Sparse Beamforming for Green Cloud-RAN
This paper proposes a new framework to design a green Cloud-RAN, which is formulated as a joint RRH selection and power minimization beamforming problem, and proposes a greedy selection algorithm, shown to provide near-optimal performance.
Learning Combinatorial Optimization Algorithms over Graphs
This paper proposes a unique combination of reinforcement learning and graph embedding that behaves like a meta-algorithm that incrementally constructs a solution, and the action is determined by the output of agraph embedding network capturing the current state of the solution.
Binary Power Control for Sum Rate Maximization over Multiple Interfering Links
To reduce the complexity of optimal binary power allocation for large networks, simple algorithms achieving 99% of the capacity promised by exhaustive binary search are provided.