提出新型神经流采样器，提升采样效率与精度。
Neural Flow Samplers with Shortcut Models
- 用带控制变量的序贯蒙特卡洛法改进不可计算项估计
- 引入捷径一致性模型，减少采样步数达30%以上
- 适合高维复杂系统采样，如分子动力学模拟
从非归一化密度中采样是广泛应用于后验推断、分子动力学模拟等领域的基础挑战。连续流式神经采样器通过学习满足边际密度演化规律（如连续性方程）的速度场来生成样本，但其学习过程需准确估计与计算困难的配分函数相关的不可计算项，现有估计器常存在高方差或低精度问题。为此，我们提出一种改进的估计器，采用基于速度的序贯蒙特卡洛方法并引入控制变量；同时，设计捷径一致性模型以降低流式神经采样器所需的采样步数。所提出的 Neural Flow Shortcut Sampler 在合成数据集和复杂n体系统目标上均优于现有流式神经采样器。
原文摘要 · Abstract (English)
Sampling from unnormalized densities presents a fundamental challenge with wide-ranging applications, from posterior inference to molecular dynamics simulations. Continuous flow-based neural samplers offer a promising approach, learning a velocity field that satisfies key principles of marginal density evolution (e.g., the continuity equation) to generate samples. However, this learning procedure requires accurate estimation of intractable terms linked to the computationally challenging partition function, for which existing estimators often suffer from high variance or low accuracy. To overcome this, we introduce an improved estimator for these challenging quantities, employing a velocity-driven Sequential Monte Carlo method enhanced with control variates. Furthermore, we introduce a shortcut consistency model to boost the runtime efficiency of the flow-based neural sampler by minimizing its required sampling steps. Our proposed Neural Flow Shortcut Sampler empirically outperforms existing flow-based neural samplers on both synthetic datasets and complex n-body system targets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。