FALCON: 连续流中少步准确的似然性
FALCON: Few-step Accurate Likelihoods for Continuous Flows
AI总结：
FALCON通过混合训练目标提升连续流的似然精度，实现高效分子采样，比现有模型快两个数量级。
摘要：
在热力学平衡下对分子状态进行可扩展采样是一个长期存在的挑战。Boltzmann生成器通过将能够进行精确似然计算的生成模型与重要采样相结合，以获得目标分布下的一致样本。当前Boltzmann生成器主要使用通过流匹配训练的连续归一化流（CNFs）来高效训练强大的模型。然而，这些模型的似然计算成本极高，每个样本需要数千次函数评估，严重限制了其应用。在本工作中，我们提出了连续流中少步准确的似然性（FALCON），该方法通过引入一种混合训练目标，鼓励可逆性，从而允许在少量步骤内进行采样，其似然精度足以满足重要采样应用的需求。我们展示了FALCON在分子Boltzmann采样中优于最先进的归一化流模型，并且比同等性能的CNF模型快两个数量级。
英文摘要：
Scalable sampling of molecular states in thermodynamic equilibrium is a long-standing challenge in statistical physics. Boltzmann Generators tackle this problem by pairing a generative model, capable of exact likelihood computation, with importance sampling to obtain consistent samples under the target distribution. Current Boltzmann Generators primarily use continuous normalizing flows (CNFs) trained with flow matching for efficient training of powerful models. However, likelihood calculation for these models is extremely costly, requiring thousands of function evaluations per sample, severely limiting their adoption. In this work, we propose Few-step Accurate Likelihoods for Continuous Flows (FALCON), a method which allows for few-step sampling with a likelihood accurate enough for importance sampling applications by introducing a hybrid training objective that encourages invertibility. We show FALCON outperforms state-of-the-art normalizing flow models for molecular Boltzmann sampling and is two orders of magnitude faster than the equivalently performing CNF model.
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。
