Middle East AI

Topics

Scientific Discovery

1 article RSS ↗

Diffusion-BBO: Diffusion-Based Inverse Modeling for Online Black-Box Optimization

arXiv · · Research RL

This paper introduces Diffusion-BBO, a new online black-box optimization (BBO) framework that uses a conditional diffusion model as an inverse surrogate model. The framework employs an Uncertainty-aware Exploration (UaE) acquisition function to propose scores in the objective space for conditional sampling. The approach is shown theoretically to achieve a near-optimal solution and empirically outperforms existing online BBO baselines across 6 scientific discovery tasks.