2021/01/03 by Seyedrazieh Bayati, Bayati, Seyedrazieh, Faramarz Jabbarvaziri +1 · 1 citation
Computer Science · Engineering · Mathematics · #Advanced Multi-Objective Optimization Algorithms #Advanced Neural Network Applications #Algorithm #Artificial intelligence #Artificial neural network #Computation #Computer science #Constrained optimization #Constrained optimization problem #Deep learning #FOS: Computer and information sciences #Focus (optics) #Gradient descent #Industrial Vision Systems and Defect Detection #Interior point method #Machine Learning (cs.LG) #Machine Learning and Algorithms #Machine learning #Manufacturing Process and Optimization #Mathematical optimization #Mathematics #Metaheuristic Optimization Algorithms Research #Optimization problem #Point (geometry) #Task (project management) #cs.LG
paper · pdf · doi:10.48550/arxiv.2101.00744
published in arXiv (Cornell University) (Cornell University) · 7 pages, 6 figures
arxiv created 2021/01/04 · openalex publication_date 2021/01/04 · arxiv updated 2021/01/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/08
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.