Learning to Optimize with Unsupervised Learning: Training Deep Neural Networks for URLLC
This addresses the need for accurate, real-time optimization in time-sensitive applications like URLLC, representing an incremental improvement by shifting from supervised to unsupervised learning.
The paper tackles the problem of inaccurate solutions from supervised learning-to-optimize methods for real-time numerical optimization, proposing an unsupervised deep learning framework that uses optimal solution properties as implicit supervision, and demonstrates it achieves ultra-high reliability in ultra-reliable and low-latency communications.
Learning the optimized solution as a function of environmental parameters is effective in solving numerical optimization in real time for time-sensitive applications. Existing works of learning to optimize train deep neural networks (DNN) with labels, and the learnt solution are inaccurate, which cannot be employed to ensure the stringent quality of service. In this paper, we propose a framework to learn the latent function with unsupervised deep learning, where the property that the optimal solution should satisfy is used as the "supervision signal" implicitly. The framework is applicable to both functional and variable optimization problems with constraints. We take a variable optimization problem in ultra-reliable and low-latency communications as an example, which demonstrates that the ultra-high reliability can be supported by the DNN without supervision labels.