BNEM:基于Bootstrap噪声能量匹配的玻尔兹曼采样器
BNEM: A Boltzmann Sampler Based on Bootstrapped Noised Energy Matching
AI总结:
BNEM通过基于噪声能量匹配的Bootstrap技术,在分子动力学等应用中实现高效且鲁棒的采样性能。
摘要:
开发一种能够从玻尔兹曼分布中生成独立同分布(IID)样本的高效采样器是科学研究中的关键挑战,例如分子动力学。在本工作中,我们旨在基于能量函数学习神经采样器,而不是从玻尔兹曼分布中采样的数据。通过学习噪声数据的能量,我们提出了一种基于扩散的采样器,即噪声能量匹配(NEM),理论上相比相关工作具有更低的方差和更高的复杂度。此外,一种新的Bootstrap技术被应用于NEM,以在偏差和方差之间取得平衡。我们评估了NEM和BNEM在二维40高斯混合模型(GMM)和四粒子双井势(DW-4)上的实验结果表明,BNEM能够实现最先进的性能,同时更加稳健。
英文摘要:
Developing an efficient sampler capable of generating independent and identically distributed (IID) samples from a Boltzmann distribution is a crucial challenge in scientific research, e.g. molecular dynamics. In this work, we intend to learn neural samplers given energy functions instead of data sampled from the Boltzmann distribution. By learning the energies of the noised data, we propose a diffusion-based sampler, Noised Energy Matching, which theoretically has lower variance and more complexity compared to related works. Furthermore, a novel bootstrapping technique is applied to NEM to balance between bias and variance. We evaluate NEM and BNEM on a 2-dimensional 40 Gaussian Mixture Model (GMM) and a 4-particle double-well potential (DW-4). The experimental results demonstrate that BNEM can achieve state-of-the-art performance while being more robust.
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。