Only Project Once: Projection-Adaptive Loss for Exact Constraint Satisfaction

cs.LG, cs.AI, cs.CE

Submitted: 2026-10-03

Updated: 2026-10-03

Comments: 36 pages, 11 figures, 12 tables. Code: https://github.com/IDEALLab/projection-adaptive-loss

Code: https://github.com/IDEALLab/projection-adaptive-loss

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• An adaptive augmented Lagrangian method for training physics and equality constrained artificial neural networks
• SnareNet: Flexible Repair Layers for Neural Networks with Hard Constraints
• LTX-Video: Realtime Video Latent Diffusion
• Neural reparameterization improves structural optimization
• ENFORCE: Nonlinear Constrained Learning with Adaptive-depth Neural Projection
• HardNet: Hard-Constrained Neural Networks with Universal Approximation Guarantees
• Pretrained Video Models as Differentiable Physics Simulators for Urban Wind Flows
• BlendedNet++: A dataset and benchmark for field-resolved aerodynamics and inverse design of blended wing body aircraft
• ACE: A fast, skillful learned global atmospheric model for climate prediction

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks