提出自洽损失方法，高效学习扩散桥的条件动态。
Control Consistency Losses for Diffusion Bridges
- 基于最优控制自洽性设计损失函数
- 无需梯度传播即可在线迭代训练
- 适合罕见事件建模，通用性强
给定初始和终态条件下模拟扩散过程的条件动态，是科学领域的重要但具有挑战性的问题。尤其在稀有事件场景中，无条件扩散过程极少能达到目标状态。本文提出一种新方法，基于最优控制的自洽性来学习扩散桥。该算法以迭代在线方式学习条件动态，无需对模拟轨迹进行梯度传播，在多种实验设置中表现优异。此外，本文还揭示了所提自洽框架与广义随机最优控制领域近期进展的联系。
原文摘要 · Abstract (English)
Simulating the conditioned dynamics of diffusion processes, given their initial and terminal states, is an important but challenging problem in the sciences. The difficulty is particularly pronounced for rare events, for which the unconditioned dynamics rarely reach the terminal state. In this work, we propose a novel approach for learning diffusion bridges based on a self-consistency property of the optimal control. The resulting algorithm learns the conditioned dynamics in an iterative online manner, and exhibits strong performance in a range of empirical settings without requiring differentiation through simulated trajectories. Beyond the diffusion bridge setting, we draw connections between our self-consistency framework and recent advances in the wider stochastic optimal control literature.
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。