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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Grontas, Panagiotis D., Terpin, Antonio, Balta, Efe C., D'Andrea, Raffaello, Lygeros, John
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911452700344320
author Grontas, Panagiotis D.
Terpin, Antonio
Balta, Efe C.
D'Andrea, Raffaello
Lygeros, John
author_facet Grontas, Panagiotis D.
Terpin, Antonio
Balta, Efe C.
D'Andrea, Raffaello
Lygeros, John
contents We introduce an output layer for neural networks that ensures satisfaction of convex constraints. Our approach, $Π$net, leverages operator splitting for rapid and reliable projections in the forward pass, and the implicit function theorem for backpropagation. We deploy $Π$net as a feasible-by-design optimization proxy for parametric constrained optimization problems and obtain modest-accuracy solutions faster than traditional solvers when solving a single problem, and significantly faster for a batch of problems. We surpass state-of-the-art learning approaches by orders of magnitude in terms of training time, solution quality, and robustness to hyperparameter tuning, while maintaining similar inference times. Finally, we tackle multi-vehicle motion planning with non-convex trajectory preferences and provide $Π$net as a GPU-ready package implemented in JAX.
format Preprint
id arxiv_https___arxiv_org_abs_2508_10480
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Pinet: Optimizing hard-constrained neural networks with orthogonal projection layers
Grontas, Panagiotis D.
Terpin, Antonio
Balta, Efe C.
D'Andrea, Raffaello
Lygeros, John
Machine Learning
Artificial Intelligence
Optimization and Control
We introduce an output layer for neural networks that ensures satisfaction of convex constraints. Our approach, $Π$net, leverages operator splitting for rapid and reliable projections in the forward pass, and the implicit function theorem for backpropagation. We deploy $Π$net as a feasible-by-design optimization proxy for parametric constrained optimization problems and obtain modest-accuracy solutions faster than traditional solvers when solving a single problem, and significantly faster for a batch of problems. We surpass state-of-the-art learning approaches by orders of magnitude in terms of training time, solution quality, and robustness to hyperparameter tuning, while maintaining similar inference times. Finally, we tackle multi-vehicle motion planning with non-convex trajectory preferences and provide $Π$net as a GPU-ready package implemented in JAX.
title Pinet: Optimizing hard-constrained neural networks with orthogonal projection layers
topic Machine Learning
Artificial Intelligence
Optimization and Control
url https://arxiv.org/abs/2508.10480