arXiv AI
Stochastic Penalty-Barrier Method for Constrained Machine Learning
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
6d ago
A Tutorial on Physics Constrained Machine Learning for Hybrid Modeling, Optimization, and Control
arXiv:2610.32914v1 Announce Type: new Abstract: Physics-constrained machine learning (PCML) integrates domain knowledge, first-principles, and physical constraints into AI/ML models. In this work, we...
arXiv Machine Learning
Jun 15
Neural Slack Variables for Shape Constraints
arXiv:2606. 13803v1 Announce Type: new Abstract: Enforcing functional inequality constraints such as monotonicity and convexity in neural networks is a fundamental challenge in many industrial and scientific applications.
arXiv AI
Aug 28
CG4AI: A Column Generation Framework for Training AI Models Under Constraints
CG4AI is a column generation framework that trains AI models while enforcing linear constraints on their outputs. It constructs a convex combination of models, using a master linear program to set mixture weights and a pricing subproblem to generate new models guided by dual variables, focusing on the most violated constraints. The method is applied to MNIST digit classification—demonstrating constraint learning, adversarial robustness, error correction, and output relabeling—and to multi‑commodity flow routing, achieving feasible predictors with higher accuracy than single‑model baselines.
arXiv Machine Learning
Jul 17
Primal-dual algorithm for contextual stochastic combinatorial optimization
arXiv:2505. 04757v2 Announce Type: replace Abstract: This paper introduces a novel approach to contextual stochastic optimization, integrating operations research and machine learning to address decision-making under uncertainty.
arXiv Machine Learning
Sep 29
Gradient Surgery for Physics-Informed Neural Networks
The paper introduces PAM-GS, a physics-aware gradient surgery technique for Physics-Informed Neural Networks (PINNs). It addresses the highly imbalanced multi-task optimisation problem in PINNs by adaptively mitigating task interference based on observed gradient conflicts. Experiments on four PDE benchmarks show that PAM-GS achieves competitive solution accuracy while maintaining strong task-balanced performance, outperforming existing methods on most problems.
arXiv Machine Learning
5d ago
Position: Adopt Constraints Over Fixed Penalties in Deep Learning
The paper argues against using fixed weighted-sum penalties to enforce constraints in deep learning, citing three main issues: non-equivalence of penalized and constrained problems in non-convex settings, difficulty in selecting appropriate penalty coefficients, and the softening of hard requirements. It contends that these problems can lead to non-compliance and relaxed constraints. The authors recommend directly solving the constrained problem when non-negotiable requirements are present.