方差缩减流匹配的时间对偶一致性

摘要

诸如扩散模型、流匹配和整流流等连续时间生成模型，虽能学习时间依赖的向量场，但其训练目标通常将不同时间步视为独立处理，导致估计量方差过高且采样效率低下。现有方法通过显式平滑惩罚、轨迹正则化或修正概率路径与求解器来缓解此问题。我们提出时序配对一致性（TPC）这一轻量级降方差原理：该技术通过耦合同一概率路径上配对时间步的速度预测，完全在估计量层面运作，无需修改模型架构、概率路径或求解器。理论分析表明，TPC会诱导产生一种二次型的轨迹耦合正则化，可在保持流匹配目标不变的同时有效降低梯度方差。在流匹配框架中实例化TPC后，其在CIFAR-10和ImageNet多个分辨率数据集上均提升了样本质量与效率，在相同或更低计算成本下获得比现有方法更低的FID指标，并可无缝扩展至包含噪声增强训练、基于分数的去噪及整流流的现代SOTA级流程。

English

Continuous-time generative models, such as diffusion models, flow matching, and rectified flow, learn time-dependent vector fields but are typically trained with objectives that treat timesteps independently, leading to high estimator variance and inefficient sampling. Prior approaches mitigate this via explicit smoothness penalties, trajectory regularization, or modified probability paths and solvers. We introduce Temporal Pair Consistency (TPC), a lightweight variance-reduction principle that couples velocity predictions at paired timesteps along the same probability path, operating entirely at the estimator level without modifying the model architecture, probability path, or solver. We provide a theoretical analysis showing that TPC induces a quadratic, trajectory-coupled regularization that provably reduces gradient variance while preserving the underlying flow-matching objective. Instantiated within flow matching, TPC improves sample quality and efficiency across CIFAR-10 and ImageNet at multiple resolutions, achieving lower FID at identical or lower computational cost than prior methods, and extends seamlessly to modern SOTA-style pipelines with noise-augmented training, score-based denoising, and rectified flow.

方差缩减流匹配的时间对偶一致性

Temporal Pair Consistency for Variance-Reduced Flow Matching

摘要

Support