# Constrained Neural Parameterization for Optimization in Function Spaces

arXiv: https://arxiv.org/abs/2606.00855 · HTML: https://mlsanity.com/paper/2606.00855/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 May 2026.

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

- [Finite basis physics-informed neural networks with hard constraints for viscous fluid flow in highly perforated domains](https://mlsanity.com/paper/2608.08114/) (2026)
- [SLP-ProbHard: Probabilistic Hard-Constrained Learning via Structural Latent Parameterization](https://mlsanity.com/paper/2609.33515/) (2026)

## Abstract (arXiv)

We propose constrained neural parameterization schemes for several classes of constraints arising in optimization problems in function spaces. This is achieved by constructing smooth neural parameterizations whose image lies entirely in the admissible set while remaining asymptotically dense. In this way, the original constrained optimization problem is transformed into a smooth unconstrained problem in parameter space, enabling efficient gradient-based optimization without penalty parameters or Lagrange multipliers. We develop geometric constructions for polyhedral constraint sets in Hilbert spaces, propose smooth neural architectures for some pointwise constraints, and introduce an exact reduced neural formulation for PDE constraints that admit a separable structure. Numerical experiments demonstrate the effectiveness of the proposed methods.