Diffusion-based learning framework for Constrained Nonconvex Optimization with Weighted Bootstrapped Refinement

ArXi:2502.10330v4 Announce Type: replace Recent advances in diffusion models show promising potential to accelerate nonconvex problem solving by leveraging their multimodality. However, most existing diffusion-based optimization approaches rely on supervised learning and lack a mechanism to enforce constraint satisfaction, which is required in real-world applications.