Denoising as Projection: Constrained Optimization with Gradient-Guided Diffusion
cs.LG, cs.AI, math.OC
Submitted: 2026-08-30
Updated: 2026-09-11
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Constrained Diffusion Models with Primal-Dual Inference
- Landing with the Score: Riemannian Optimization through Denoising
- Aligning Diffusion Model with Problem Constraints for Trajectory Optimization
- Iterative Tilting for Diffusion Fine-Tuning
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