Dual Domain Learning of Optimal Resource Allocations in Wireless Systems

• Published in: Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) pp. 4729 - 4733
• Main Authors: Eisen, Mark, Zhang, Clark, Chamon, Luiz F. O., Lee, Daniel D., Ribeiro, Alejandro
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.05.2019
• Subjects: duality gap; leaning; Machine learning; Neural networks; Numerical models; Numerical simulation; Optimization; resource allocation; Resource management; Signal processing; Signal processing algorithms; Speech processing; Wireless communication; wireless communications
• ISSN: 2379-190X
• DOI: 10.1109/ICASSP.2019.8683150

We consider the problem of finding optimal resource allocations subject to system constraints in a generic class of problems in wireless communications. These problems are inherently challenging due to functional optimization and potential non-convexities. However, these problems can be observed to take the form of a regression problem, although one in which the statistical loss function appears as a constraint. This motivates the use of machine learning model parameterizations. To apply gradient-based solution algorithms that do not require model knowledge, we convert the constrained optimization problem to an unconstrained one using Lagrangian duality. Despite the non-convexity in the problem, we formally show that the sub-optimality of the dual domain problem is small when the learning parameterization is sufficiently dense. We then present a primal-dual learning algorithm that looks for solutions to the dual problem using model-free gradient estimates. In a numerical simulation, we demonstrate the near-optimality of the proposed model-free algorithm using a neural network parametrization for a capacity maximization problem.