Reward-Directed Conditional Diffusion: Provable Distribution Estimation and Reward Improvement

Understand

We explore the methodology and theory of reward-directed generation via conditional diffusion models.

• Directed generation aims to generate samples with desired properties as measured by a reward function, which has broad applications in generative AI, reinforcement learning, and computational biology.
• We consider the common learning scenario where the data set consists of unlabeled data along with a smaller set of data with noisy reward labels.
• Our approach leverages a learned reward function on the smaller data set as a pseudolabeler.