arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2409.20423stat.MLcs.AIcs.LG
收藏

基于高斯过程的流级别流匹配

Stream-level flow matching with Gaussian processes

Duke University(杜克大学)

Ganchao Wei, Li Ma

AI总结:

本文扩展了条件流匹配算法,通过引入高斯过程对连接源和目标数据对的潜在随机路径(流)进行建模,有效降低了边缘向量场的估计方差,提升了生成样本质量,并支持灵活连接相关训练数据点。

摘要:

流匹配(FM)是一类用于拟合连续归一化流(CNFs)的训练算法。条件流匹配(CFM)利用了这样一个事实:CNF的边缘向量场可以通过对给定流路径一端或两端所指定的条件向量场进行最小二乘回归拟合来学习。在本文中,我们通过沿“流”定义条件概率路径来扩展CFM算法,这些“流”是连接源和目标数据对的潜在随机路径的实例,并使用高斯过程(GP)分布对其进行建模。GP独特的分布特性有助于保持CFM训练的“免模拟”性质。我们表明,这种CFM的泛化能够以适度的计算成本有效降低估计边缘向量场的方差,从而在常见指标下提升生成样本的质量。此外,在流上采用GP允许灵活地连接多个相关的训练数据点(例如时间序列)。我们通过模拟以及在图像和神经时间序列数据上的应用,实证验证了我们的主张。

英文摘要:

Flow matching (FM) is a family of training algorithms for fitting continuous normalizing flows (CNFs). Conditional flow matching (CFM) exploits the fact that the marginal vector field of a CNF can be learned by fitting least-squares regression to the conditional vector field specified given one or both ends of the flow path. In this paper, we extend the CFM algorithm by defining conditional probability paths along ``streams'', instances of latent stochastic paths that connect data pairs of source and target, which are modeled with Gaussian process (GP) distributions. The unique distributional properties of GPs help preserve the ``simulation-free" nature of CFM training. We show that this generalization of the CFM can effectively reduce the variance in the estimated marginal vector field at a moderate computational cost, thereby improving the quality of the generated samples under common metrics. Additionally, adopting the GP on the streams allows for flexibly linking multiple correlated training data points (e.g., time series). We empirically validate our claim through both simulations and applications to image and neural time series data.

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。

↑