• Corpus ID: 238857058

Stability Analysis of Unfolded WMMSE for Power Allocation

  title={Stability Analysis of Unfolded WMMSE for Power Allocation},
  author={Arindam Chowdhury and Fernando Gama and Santiago Segarra},
Power allocation is one of the fundamental problems in wireless networks and a wide variety of algorithms address this problem from different perspectives. A common element among these algorithms is that they rely on an estimation of the channel state, which may be inaccurate on account of hardware defects, noisy feedback systems, and environmental and adversarial disturbances. Therefore, it is essential that the output power allocation of these algorithms is stable with respect to input… 

Figures from this paper


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.
ML-aided power allocation for Tactical MIMO
A UWMMSE framework for power allocation in (multiple-input multiple-output) MIMO interference networks is presented and a major advantage lies in its use of low-complexity learnable systems in which the number of parameters scales linearly with respect to the hidden layer size of embedded neural architectures.
Deep unfolding of the weighted MMSE beamforming algorithm
This work proposes the novel application of deep unfolding to the WMMSE algorithm for a MISO downlink channel, and presents an alternative formulation that circumvents these operations by resorting to projected gradient descent.
A Graph Neural Network Approach for Scalable Wireless Power Control
This paper proposes an interference graph convolutional neural network (IGCNet) to learn the optimal power control in an unsupervised manner and shows that one- layer IGCNet is a universal approximator to continuous set functions, which well matches the permutation invariance property of interference channels and it is robust to imperfect channel state information (CSI).
Dynamic Spectrum Management: Complexity and Duality
  • Z. Luo, Shuzhong Zhang
  • Mathematics, Computer Science
    IEEE Journal of Selected Topics in Signal Processing
  • 2008
Using the Lyapunov theorem in functional analysis, this work rigorously proves a result first discovered by Yu and Lui (2006) that there is a zero duality gap for the continuous (Lebesgue integral) formulation of the discretized version of this nonconvex problem.
Learning to Optimize: Training Deep Neural Networks for Interference Management
Numerical optimization has played a central role in addressing key signal processing (SP) problems. Highly effective methods have been developed for a large variety of SP applications such as
Characterization of Convex and Concave Resource Allocation Problems in Interference Coupled Wireless Systems
The paper shows that under certain natural assumptions, the exponential transformation is the unique transformation for “convexification” of resource allocation problems for linear interference functions.
Adaptive Contention Window Design Using Deep Q-Learning
A rainbow agent is implemented, which incorporates several empirical improvements over the basic deep Q-network and performs close to optimal and markedly improves upon existing learning and non-learning based alternatives.
Stability Properties of Graph Neural Networks
This work proves that graph convolutions with integral Lipschitz filters, in combination with the frequency mixing effect of the corresponding nonlinearities, yields an architecture that is both stable to small changes in the underlying topology, and discriminative of information located at high frequencies.
Capacity and power allocation for fading MIMO channels with channel estimation error
Lower and upper bounds of mutual information under channel estimation error and tight lower bounds of ergodic and outage capacities and optimal transmitter power allocation strategies that achieve the bounds under perfect feedback are studied.