arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.05174stat.MLcs.AIcs.LGmath.STstat.TH
收藏

Riemannian流匹配的总变分速率

Total Variation Rates for Riemannian Flow Matching

Rice University(莱斯大学);University of California, Davis(加州大学戴维斯分校)

Yunrui Guan, Krishnakumar Balasubramanian, Shiqian Ma

AI总结:

该研究提出了Riemannian流匹配的总变分收敛分析,通过非渐近的理论框架,分离了数值离散化误差与学习误差,实现了在流形上的显式多项式迭代复杂度。

摘要:

Riemannian流匹配(RFM)通过学习一个时间依赖的切向量场,将基于流的生成模型扩展到支撑在流形上的数据。我们开发了一种非渐近的总变分(TV)收敛分析,用于使用学习的向量场和欧拉离散化在流形上进行采样。我们的关键技术成分是支配两个流形ODE流之间TV演化的微分不等式,它通过向量场不匹配的散度和参考流的分数来表达TV的时间导数;控制这些项需要建立新的界限,这些界限明确考虑了平行运输和曲率。在对流匹配场的总体光滑性假设以及对学习场的均匀(紧致流形)或均方(Hadamard流形)近似保证下,我们得到形式为TV ≤ C_Lip h + C_ε ε(在紧致流形上还有一个额外的更高阶ε²项)的显式界限,清晰地分离了数值离散化和学习误差。实例化结果在超球面S^d上和满足温和矩条件的SPD(n)流形上得到显式的多项式迭代复杂度。

英文摘要:

Riemannian flow matching (RFM) extends flow-based generative modeling to data supported on manifolds by learning a time-dependent tangent vector field whose flow-ODE transports a simple base distribution to the data law. We develop a nonasymptotic Total Variation (TV) convergence analysis for RFM samplers that use a learned vector field together with Euler discretization on manifolds. Our key technical ingredient is a differential inequality governing the evolution of TV between two manifold ODE flows, which expresses the time-derivative of TV through the divergence of the vector-field mismatch and the score of the reference flow; controlling these terms requires establishing new bounds that explicitly account for parallel transport and curvature. Under smoothness assumptions on the population flow-matching field and either uniform (compact manifolds) or mean-square (Hadamard manifolds) approximation guarantees for the learned field, we obtain explicit bounds of the form $\mathrm{TV}\le C_{\mathrm{Lip}}\,h + C_{\varepsilon}\,\varepsilon$ (with an additional higher-order $\varepsilon^2$ term on compact manifolds), cleanly separating numerical discretization and learning errors. Here, $h$ is the step-size and $\varepsilon$ is the target accuracy. Instantiations yield \emph{explicit} polynomial iteration complexities on the hypersphere $S^d$, and on the SPD$(n)$ manifolds under mild moment conditions.

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。

↑