Annealing Flow Generative Models Towards Sampling High-Dimensional and Multi-Modal Distributions

Understand

Sampling from high-dimensional, multi-modal distributions remains a fundamental challenge across domains such as statistical Bayesian inference and physics-based machine learning.

• In this paper, we propose Annealing Flow (AF), a method built on Continuous Normalizing Flow (CNF) for sampling from high-dimensional and multi-modal distributions.
• AF is trained with a dynamic Optimal Transport (OT) objective incorporating Wasserstein regularization, and guided by annealing procedures, facilitating effective exploration of modes in high-dimensional spaces.
• Compared to recent NF methods, AF greatly improves training efficiency and stability, with minimal reliance on MC assistance.