However, these methods typically rely on strict assumptions and are limited to certain types of label noise. In this paper, we reformulate the label-noise problem from a generative-model perspective, i.e., labels are generated by gradually refining an initial random guess.

TRPO, PPO), and a critic that involves minimizing a closely connected objective.

Most previous work on federated learning assumes that clients possess static batches of training data. However, clients may also need to make real-time predictions on streaming data in non-stationary environments.

Generative diffusion models have recently emerged as a leading approach for generating high-dimensional data.