TRADE：利用归一化流在外部条件之间进行分布迁移
TRADE: Transfer of Distributions between External Conditions with Normalizing Flows
AI总结：
本文提出 TRADE 方法，将依赖外部参数的分布学习建模为边值问题，利用归一化流和未归一化密度梯度在不同条件间传播分布信息，从而在无需限制性架构或基于能量训练的情况下，高效学习参数依赖分布，并在贝叶斯推断、分子模拟和物理晶格模型等任务中取得优异效果。
摘要：
对外部控制参数存在依赖的分布进行建模，是分子模拟等多种应用中的常见场景，例如温度等系统属性会影响分子构型。尽管这些应用具有重要相关性，现有解决方案仍不尽如人意，因为它们要么要求严重受限的模型架构，要么依赖基于能量的训练，而后者容易不稳定。我们提出 TRADE，通过将学习过程形式化为一个边值问题来克服这些局限。首先使用独立同分布样本或反向 KL 训练针对特定条件训练模型，从而建立一个边界分布。随后，我们利用未归一化密度关于外部参数的梯度，将该信息传播到其他条件。这种形式化方式类似于物理信息神经网络的原理，使我们能够在没有限制性假设的情况下高效地学习依赖参数的分布。在实验上，我们证明 TRADE 在从贝叶斯推断、分子模拟到物理晶格模型的广泛应用中都取得了优异结果。
英文摘要：
Modeling distributions that depend on external control parameters is a common scenario in diverse applications like molecular simulations, where system properties like temperature affect molecular configurations. Despite the relevance of these applications, existing solutions are unsatisfactory as they require severely restricted model architectures or rely on energy-based training, which is prone to instability. We introduce TRADE, which overcomes these limitations by formulating the learning process as a boundary value problem. By initially training the model for a specific condition using either i.i.d.~samples or backward KL training, we establish a boundary distribution. We then propagate this information across other conditions using the gradient of the unnormalized density with respect to the external parameter. This formulation, akin to the principles of physics-informed neural networks, allows us to efficiently learn parameter-dependent distributions without restrictive assumptions. Experimentally, we demonstrate that TRADE achieves excellent results in a wide range of applications, ranging from Bayesian inference and molecular simulations to physical lattice models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
