score-based-models

This paper proposes primal-dual inference for constrained diffusion models, jointly inferring the optimal distribution and its dual variable via a dual-conditioned score network, with convergence guarantees and applications in wireless resource allocation and portfolio management.

This arXiv preprint proposes a unified measure-theoretic framework for understanding diffusion, score-based, and flow matching generative models. It establishes connections between these methods via continuity/Fokker-Planck equations and analyzes their sampling schemes and theoretical guarantees.