温度退火玻尔兹曼生成器
Temperature-Annealed Boltzmann Generators
AI总结：
针对分子系统玻尔兹曼分布采样易模式崩溃的问题，提出温度退火玻尔兹曼生成器，通过高温训练避免模式崩溃，结合重加权目标退火分布，在多分子系统中以更少能耗实现更优采样效果。
摘要：
对未归一化概率密度（如分子系统的玻尔兹曼分布）进行高效采样是一项长期存在的挑战。除了分子动力学或马尔可夫链蒙特卡洛等传统方法外，还引入了变分方法，例如使用反向Kullback-Leibler散度训练归一化流。然而，这类方法容易出现模式崩溃，通常无法学会对整个构象空间进行采样。在此，我们提出温度退火玻尔兹曼生成器（TA-BG）来解决这一挑战。首先，我们证明在高温下使用反向Kullback-Leibler散度训练归一化流是可行的，且不会出现模式崩溃。此外，我们引入了一种基于重加权的训练目标，用于将分布退火至更低的目标温度。我们将该方法应用于三个复杂度递增的分子系统，与基线相比，几乎在所有指标上都取得了更好的结果，同时所需的目标能量评估次数最多减少三分之二。对于最大的系统，我们的方法是唯一能准确解析该系统亚稳态的方法。
英文摘要：
Efficient sampling of unnormalized probability densities such as the Boltzmann distribution of molecular systems is a longstanding challenge. Next to conventional approaches like molecular dynamics or Markov chain Monte Carlo, variational approaches, such as training normalizing flows with the reverse Kullback-Leibler divergence, have been introduced. However, such methods are prone to mode collapse and often do not learn to sample the full configurational space. Here, we present temperature-annealed Boltzmann generators (TA-BG) to address this challenge. First, we demonstrate that training a normalizing flow with the reverse Kullback-Leibler divergence at high temperatures is possible without mode collapse. Furthermore, we introduce a reweighting-based training objective to anneal the distribution to lower target temperatures. We apply this methodology to three molecular systems of increasing complexity and, compared to the baseline, achieve better results in almost all metrics while requiring up to three times fewer target energy evaluations. For the largest system, our approach is the only method that accurately resolves the metastable states of the system.
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。
