Newton Matching for Generative Modeling: A Unified Framework for Fine-Tuning and Sampling

Zeyang Li, Yunan Wang, Paolo Giaretta +1

We develop Newton Matching, a unified framework for fine-tuning and sampling in generative modeling. The target is $\pi \propto \mu e^{\tau r}$, where $r$ is the reward, $\tau >0$ the inverse tem…