Learning to Optimize Under Constraints with Unsupervised Deep Neural Networks

TL;DR

This paper introduces an unsupervised deep learning approach to solve constrained continuous optimization problems efficiently in real-time, especially when problem parameters change frequently, by enforcing constraints during the learning process.

Contribution

It presents a novel method to incorporate equality and inequality constraints into deep learning solutions for generic optimization problems, enabling real-time applications.

Findings

Enables real-time constrained optimization with deep learning.

Reduces computational complexity during online optimization.

Successfully enforces constraints in DL-generated solutions.

Abstract

In this paper, we propose a machine learning (ML) method to learn how to solve a generic constrained continuous optimization problem. To the best of our knowledge, the generic methods that learn to optimize, focus on unconstrained optimization problems and those dealing with constrained problems are not easy-to-generalize. This approach is quite useful in optimization tasks where the problem's parameters constantly change and require resolving the optimization task per parameter update. In such problems, the computational complexity of optimization algorithms such as gradient descent or interior point method preclude near-optimal designs in real-time applications. In this paper, we propose an unsupervised deep learning (DL) solution for solving constrained optimization problems in real-time by relegating the main computation load to offline training phase. This paper's main contribution is proposing a method for enforcing the equality and inequality constraints to the DL-generated solutions for generic optimization tasks.