# KKT-Informed Neural Network

arXiv: https://arxiv.org/abs/2409.09087 · HTML: https://mlsanity.com/paper/2409.09087/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 5 references that are in the map.
- First posted on arXiv 11 Sep 2024.

## Builds on (most cited first, 4 of 4)

- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Differentiable Convex Optimization Layers](https://mlsanity.com/paper/1910.12430/) (2019)
- [Gym-ANM: Reinforcement Learning Environments for Active Network Management Tasks in Electricity Distribution Systems](https://mlsanity.com/paper/2103.07932/) (2021)
- [Jacobian Descent for Multi-Objective Optimization](https://mlsanity.com/paper/2406.16232/) (2024)

## Built on by (most cited first, 2 of 2)

- [Limitations of Physics-Informed Neural Networks: a Study on Smart Grid Surrogation](https://mlsanity.com/paper/2508.21559/) (2025)
- [Optimizing Energy Management of Smart Grid using Reinforcement Learning aided by Surrogate models built using Physics-informed Neural Networks](https://mlsanity.com/paper/2510.17380/) (2025)

## Abstract (arXiv)

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.