English

Soft-Radial Projection for Constrained End-to-End Learning

Machine Learning 2026-02-04 v1 Optimization and Control Computational Finance Machine Learning

Abstract

Integrating hard constraints into deep learning is essential for safety-critical systems. Yet existing constructive layers that project predictions onto constraint boundaries face a fundamental bottleneck: gradient saturation. By collapsing exterior points onto lower-dimensional surfaces, standard orthogonal projections induce rank-deficient Jacobians, which nullify gradients orthogonal to active constraints and hinder optimization. We introduce Soft-Radial Projection, a differentiable reparameterization layer that circumvents this issue through a radial mapping from Euclidean space into the interior of the feasible set. This construction guarantees strict feasibility while preserving a full-rank Jacobian almost everywhere, thereby preventing the optimization stalls typical of boundary-based methods. We theoretically prove that the architecture retains the universal approximation property and empirically show improved convergence behavior and solution quality over state-of-the-art optimization- and projection-based baselines.

Keywords

Cite

@article{arxiv.2602.03461,
  title  = {Soft-Radial Projection for Constrained End-to-End Learning},
  author = {Philipp J. Schneider and Daniel Kuhn},
  journal= {arXiv preprint arXiv:2602.03461},
  year   = {2026}
}
R2 v1 2026-07-01T09:34:02.980Z