Learning to Optimize with Unsupervised Learning: Training Deep Neural Networks for URLLC

TL;DR

This paper introduces an unsupervised deep learning framework to optimize solutions for time-sensitive applications like URLLC, ensuring high reliability without relying on labeled data.

Contribution

It proposes a novel unsupervised learning approach that uses the properties of optimal solutions as implicit supervision, applicable to constrained optimization problems.

Findings

Supports ultra-high reliability in URLLC with unsupervised DNNs

Achieves accurate solutions without labeled training data

Demonstrates effectiveness in variable constrained optimization

Abstract

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.