提出高效计算生成模型似然的新方法，显著提升速度与稳定性。
Few-Step Boltzmann Generators via Scalable Likelihood Flow Maps
- 用可向量化的新目标替代随机估计，避免方差问题。
- 训练时间减少、性能优于现有方法，推理速度最高快10倍。
- 适合分子科学和图像生成任务，尤其看重效率的场景。
基于流的生成模型近年已实现高质量样本生成且仅需少量函数求值，但模型似然估计仍缺乏类似进展。现有方法或依赖受限架构以实现精确计算，或使用如Hutchinson迹估计等随机近似，引入较大方差。本文提出SCALLOP（SCAlable LikeLihood distillation of flOw maPs），基于最近提出的F2D2模型，该模型可在少量求值下同时生成样本与密度。尽管F2D2训练中使用Hutchinson估计，我们引入一种无Hutchinson的可扩展似然蒸馏目标，并支持向量化计算。实验表明，SCALLOP在分子科学中作为玻尔兹曼生成器表现优异，图像数据集上也验证其优势：相比F2D2显著降低训练方差与时间，性能持续提升，且相较当前最优方法保持竞争力，推理速度最高达最快基线的10倍。
原文摘要 · Abstract (English)
Recent progress in flow-based generative modeling has led to models that output high-quality samples while using only a small number of function evaluations. However, at present, there is a lack of similar advances in estimating the model likelihood. In particular, most existing methods either rely on restrictive architectures that enable exact calculations, or use stochastic approximations such as Hutchinson's trace estimator that introduce substantial variance. In this work, we introduce SCAlable LikeLihood distillation of flOw maPs (SCALLOP). SCALLOP builds on the recently proposed F2D2, a likelihood flow map model that can generate samples and their densities in a small number of function evaluations. While F2D2 uses Hutchinson's estimator during training, we introduce an alternative and more scalable likelihood distillation objective that is Hutchinson-free and admits a vectorized formulation. Empirically, we demonstrate the effectiveness of SCALLOP as a Boltzmann generator in molecular science, and further validate its benefit on image datasets. SCALLOP significantly reduces both training variance and training time while consistently improving performance compared to F2D2, and is competitive with the state-of-the-art while achieving up to 10x inference speedup over the fastest baseline.
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。