负载储备Wasserstein传播用于各向同性扩散采样器
Load--Reserve Wasserstein Propagation for Isotropic Diffusion Samplers
AI总结:
本文提出了一种针对各向同性反向SDE窗口的适应性传播接口,通过认证学习漂移剖面生成线性尾运输成本,结合反射耦合和Hardy容量量化负载,以改进Wasserstein距离中的收缩率和尾坡。
摘要:
许多Wasserstein分析通过学习漂移的全局稳定性总结来控制反向时间传播。这些总结可能隐藏径向几何特征:等高但宽度不同的扩展区域可能产生不同的传播成本。本文为标量各向同性反向SDE窗口提供了一种适应性传播接口,通过认证学习漂移剖面生成线性尾运输成本:反射耦合将稳定性降至一维斜率预算,Hardy容量量化在合同性尾储备前支付的负载。编译器生成适应性成本、收缩率和保留尾坡。分数模型和求解器残差被作为强迫输入,在适应的Wasserstein距离中加性传播。二次Wasserstein误差仅在终端时间报告,使用保留的尾坡与尾、矩或支撑信息。高斯平滑去噪几何提供均匀耗散、有界振幅和常见协方差混合窗口的逆半径剖面。固定高度示例表明,不利高度即使最终有储备也不决定证书;障碍示例显示负载依赖性是结构性的。
英文摘要:
Many Wasserstein analyses of diffusion samplers control reverse-time propagation by global stability summaries of the learned drift. These summaries can hide radial geometry: equal-height expansive regions of different width can yield different propagation costs. We give a profile-adapted propagation interface for scalar-isotropic reverse-SDE windows with certified learned-drift profiles. A certified lower radial profile is compiled into an affine-tail transportation cost: reflection coupling reduces stability to a one-dimensional slope budget, and Hardy capacity quantifies the load paid before a contractive tail reserve. The compiler yields an adapted cost, contraction rate, and retained tail slope. Score-modeling and solver residuals are treated as forcing inputs and propagate additively in the adapted Wasserstein distance. Quadratic Wasserstein error is reported only at terminal time, using the retained tail slope with tail, moment, or support information. Gaussian-smoothed denoising geometry supplies inverse-radius profiles for uniformly dissipative, bounded-amplitude, and common-covariance mixture windows. Fixed-height examples show that adverse height, even with eventual reserve, does not determine the certificate; barrier examples show that the load dependence is structural.
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。