SPREAD: Sampling-based Pareto front Refinement via Efficient Adaptive Diffusion

SPREAD learns a conditional diffusion model over decision variables and then iteratively refines sampled candidates during reverse diffusion to move them toward Pareto-optimal regions. At each step, it guides the samples using adaptive multiple-gradient-descent directions to improve objectives while adding a repulsion term to maintain diversity along the Pareto front.

See the project page for more details.