发表机构
ETH Zurich（苏黎世联邦理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出通过移位协变小波表示和逐样本相位条件化编码循环平稳性，并引入无训练循环平稳性指数及对偶耦合采样，以提升医学时间序列扩散恢复性能。
AI 中文摘要
许多生理时间序列，如心脏和脑部记录，表现出循环平稳性：其统计量随潜在的循环相位周期性变化。运动、接触不良和生理干扰造成的污染掩盖了诊断所需的形态，使得信号恢复至关重要。现有的扩散方法仅以受损观测为条件，必须隐式学习循环结构。我们反而提出两种编码循环平稳性的归纳偏置：一种移位协变的小波表示和从受损输入推断出的密集逐样本相位条件化。我们进一步引入一个无需训练的循环平稳性指数，用于量化相位结构并预测相位条件化何时会有帮助。最后，我们提出反向轨迹的对偶耦合以减少采样方差，同时以五倍更少的网络评估实现相当的性能。跨模态的结果表明，显式编码可测量的循环结构改善了生理时间序列的恢复。
英文摘要
Many physiological time series, such as cardiac and brain recordings, exhibit cyclostationarity: their statistics vary periodically with an underlying cycle phase. Corruption from motion, poor contact, and physiological interference obscures morphology needed for diagnosis, making signal restoration essential. Existing diffusion approaches condition on corrupted observations alone and must learn cyclic structure implicitly. We instead propose two inductive biases which encode cyclostationarity: a shift-covariant wavelet representation and dense per-sample phase conditioning inferred from the corrupted input. We further introduce a training-free cyclostationarity index that quantifies phase structure and predicts when phase conditioning will help. Finally, we propose antithetic coupling of reverse trajectories to reduce sampling variance while achieving comparable performance with fivefold fewer network evaluations. Across modalities, our results show that explicitly encoding measurable cyclic structure improves physiological time-series restoration.
Comments43 pages, 16 figures, 21 tables
