用随机桥接加速生成模型采样，少步数出高质量结果。
Random-Bridges as Stochastic Transports for Generative Models
- 以随机桥接作为概率分布间的随机传输路径，可灵活设计为马尔可夫或非马尔可夫过程。
- 基于高斯随机桥的实验在更少步骤下生成高质量样本，弗雷歇初始距离表现媲美主流方法。
- 框架计算开销小，适合高速生成任务，尤其适合对效率敏感的应用场景。
本文提出将随机桥接——在固定时间点上约束至目标分布的随机过程——应用于生成建模。随机桥接可在适当初始化下充当两概率分布间的随机传输路径，其行为可呈现马尔可夫或非马尔可夫、连续、离散或混合模式，取决于驱动过程。我们从一般概率假设出发，推导出适用于学习与模拟算法的信息处理表示形式。基于高斯随机桥的实证结果显示，在显著更少的步骤内即可生成高质量样本，且弗雷歇初始距离（FID）得分具有竞争力。分析表明，该框架计算成本低，适合高速生成任务。
原文摘要 · Abstract (English)
This paper motivates the use of random-bridges -- stochastic processes conditioned to take target distributions at fixed timepoints -- in the realm of generative modelling. Herein, random-bridges can act as stochastic transports between two probability distributions when appropriately initialized, and can display either Markovian or non-Markovian, and either continuous, discontinuous or hybrid patterns depending on the driving process. We show how one can start from general probabilistic statements and then branch out into specific representations for learning and simulation algorithms in terms of information processing. Our empirical results, built on Gaussian random bridges, produce high-quality samples in significantly fewer steps compared to traditional approaches, while achieving competitive Frechet inception distance scores. Our analysis provides evidence that the proposed framework is computationally cheap and suitable for high-speed generation tasks.
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。