KKT-Informed Neural Network

Carmine Delle Femine
9/11/2024
math.OCcs.LG

No confident code implementation found for this paper. 1 possible match can be shown below.

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Karush-Kuhn-Tucker Condition-Trained Neural Networks (KKT Nets)

86% match2024

Optimality-Informed Neural Networks for Solving Parametric Optimization Problems

85% match2025

Self-Supervised Learning of Iterative Solvers for Constrained Optimization

83% match2024

Non-Convex Optimizations for Machine Learning with Theoretical Guarantee: Robust Matrix Completion and Neural Network Learning

83% match2023

Towards graph neural networks for provably solving convex optimization problems

83% match1 repo12025

Pinet: Optimizing hard-constrained neural networks with orthogonal projection layers

83% match2025

Cite this paper

@article{femine2024kktinformed,
  title  = {KKT-Informed Neural Network},
  author = {Carmine Delle Femine},
  year   = {2024},
  eprint = {2409.09087},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2409.09087v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2409.09087.svg)](https://codeofpaper.com/paper/2409.09087)

Discussion