发表机构
Kavli Institute for Cosmology Cambridge; Institute of Astronomy, University of Cambridge（剑桥卡夫利宇宙学研究所; 剑桥大学天文研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出神经传输嵌套采样（NTNS），结合嵌套采样与神经流，高效估计高维分子系统配分函数，在Lennard-Jones簇基准上显著降低误差并恢复相结构。
AI 中文摘要
从分子系统的玻尔兹曼分布中采样是一个推断问题，近年来在神经密度估计进展的推动下取得了显著发展。我们开发了一种新颖的采样算法——神经传输嵌套采样（NTNS），它将嵌套采样的经典优势与现代基于神经流的方法相结合。NTNS 在嵌套采样外循环内部使用流匹配速度作为 Metropolis-Hastings 校正的 Langevin 核中的漂移项，仅需评估目标能量函数，即可对高维粒子系统的完整配分函数进行可扩展估计。我们在具有挑战性的分子采样基准上对 NTNS 进行了测试，规模高达包含 55 个相互作用粒子的 Lennard-Jones 簇，在此规模下，与最强的神经基线相比，NTNS 将相对于参考 MCMC 的原子间距离和能量 Wasserstein 误差降低了一个数量级以上，同时壁钟成本更低。据我们所知，NTNS 也是首个在此规模下返回经过校准的、温度分辨的配分函数估计的神经采样器，能够从单次运行中恢复跨温度相结构。
英文摘要
Sampling from Boltzmann distributions of molecular systems is an inference problem that has seen significant recent developments fuelled by advances in neural density estimation. We develop a novel sampling algorithm, Neural Transport Nested Sampling (NTNS), which combines the classical strengths of nested sampling with modern neural flow-based methods. NTNS uses a flow matching velocity as the drift in a Metropolis--Hastings corrected Langevin kernel inside a nested sampling outer loop, requiring only evaluations of the target energy function and providing scalable estimation of the full partition function of high-dimensional particle systems. We benchmark NTNS on challenging molecular sampling benchmarks, scaling up to Lennard--Jones clusters of 55 interacting particles, where it reduces both interatomic distance and energy Wasserstein errors to reference MCMC by over an order of magnitude relative to the strongest neural baselines at lower wall-clock cost. To our knowledge, NTNS is also the first neural sampler to return a calibrated, temperature resolved partition function estimate at this scale, recovering the phase structure across temperature from a single run.
Comments26 pages, 9 figures
