KKT-Informed Neural Network

2024/09/11 by Carmine Delle Femine, Femine, Carmine Delle · 2 citations
Computer Science · #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Neural Networks and Applications #Optimization and Control (math.OC)

paper · pdf · doi:10.48550/arxiv.2409.09087

openalex publication_date 2024/09/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

A neural network-based approach for solving parametric convex optimization problems is presented, where the network estimates the optimal points given a batch of input parameters. The network is trained by penalizing violations of the Karush-Kuhn-Tucker (KKT) conditions, ensuring that its predictions adhere to these optimality criteria. Additionally, since the bounds of the parameter space are known, training batches can be randomly generated without requiring external data. This method trades guaranteed optimality for significant improvements in speed, enabling parallel solving of a class of optimization problems.

Cited by

• Optimizing Energy Management of Smart Grid using Reinforcement Learning aided by Surrogate models built using Physics-informed Neural Networks
• Limitations of Physics-Informed Neural Networks: a Study on Smart Grid Surrogation

Related

• Karush-Kuhn-Tucker Condition-Trained Neural Networks (KKT Nets)
• KKT-based optimality conditions for neural network approximation
• Input Convex Neural Networks
• Non-Convex Optimizations for Machine Learning with Theoretical Guarantee: Robust Matrix Completion and Neural Network Learning
• Optimality-Informed Neural Networks for Solving Parametric Optimization Problems