CG4AI: A Column Generation Framework for Training AI Models Under Constraints
cs.LG, cs.AI, cs.DM
Submitted: 2026-08-26
Updated: 2026-08-26
Terminology
Sources
- HardNet: Hard-Constrained Neural Networks with Universal Approximation Guarantees
- RAYEN: Imposition of Hard Convex Constraints on Neural Networks
- Probably Approximately Correct Constrained Learning
- Alignment Studio: Aligning Large Language Models to Particular Contextual Regulations
- DC3: A learning method for optimization with hard constraints
- Enforcing Hard Linear Constraints in Deep Learning Models with Decision Rules
- Feed-Forward Neural Networks as a Mixed-Integer Program
- Evaluating Robustness of Neural Networks with Mixed Integer Programming
- Strong mixed-integer programming formulations for trained neural networks
- Adam: A Method for Stochastic Optimization
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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks