提出新型生成模型Annealing Flow，高效采样高维多峰分布。
Annealing Flow Generative Models Towards Sampling High-Dimensional and Multi-Modal Distributions
- 基于连续归一化流，结合动态最优传输与退火机制。
- 在高维多峰分布上训练更稳定，无需大量蒙特卡洛辅助。
- 适合复杂分布采样，尤其擅长处理难采样的极端情况。
从高维、多模态分布中采样仍是统计贝叶斯推断和基于物理的机器学习中的核心挑战。本文提出基于连续归一化流（CNF）的退火流（Annealing Flow, AF）方法，通过引入包含Wasserstein正则化的动态最优传输（OT）目标，并结合退火过程，有效促进高维空间中多个模式的探索。相比近期的归一化流方法，AF显著提升训练效率与稳定性，对蒙特卡洛（MC）辅助依赖极低。我们在多种挑战性分布及真实数据集上验证了其性能优势，尤其在高维多峰场景下表现卓越。同时展示了其在采样最不利分布方面的潜力。
原文摘要 · Abstract (English)
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. We demonstrate the superior performance of AF compared to state-of-the-art methods through experiments on various challenging distributions and real-world datasets, particularly in high-dimensional and multi-modal settings. We also highlight AF potential for sampling the least favorable distributions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。