Advances in diffusion models for generative artificial intelligence have recently propagated to the time series (TS) domain, demonstrating state-of-the-art performance on various tasks. However, prior works on TS diffusion models often borrow the framework of existing works proposed in other domains without considering the characteristics of TS data, leading to suboptimal performance. In this work, we propose Adaptive Noise schedule for Time series diffusion models (ANT), which automatically predetermines proper noise schedules for given TS datasets based on their statistics representing non-stationarity. Our intuition is that an optimal noise schedule should satisfy the following desiderata: 1) It linearly reduces the non-stationarity of TS data so that all diffusion steps are equally meaningful, 2) the data is corrupted to the random noise at the final step, and 3) the number of steps is sufficiently large. The proposed method is practical for use in that it eliminates the necessity of finding the optimal noise schedule with a small additional cost to compute the statistics for given datasets, which can be done offline before training. We validate the effectiveness of our method across various tasks, including TS forecasting, refinement, and generation, on datasets from diverse domains. Code is available at this repository: https://github.com/seunghan96/ANT.

翻译：生成式人工智能中扩散模型的进展最近已扩展到时间序列（TS）领域，并在多项任务中展现出最先进的性能。然而，先前关于时间序列扩散模型的研究往往直接套用其他领域提出的现有框架，未能充分考虑时间序列数据的特性，导致性能未能达到最优。本文提出面向时间序列扩散模型的自适应噪声调度方法（ANT），该方法能基于表征非平稳性的数据集统计特征，自动为给定时间序列数据集预先确定合适的噪声调度方案。我们的核心观点是：最优噪声调度应满足以下要求：1）线性降低时间序列数据的非平稳性，使所有扩散步骤具有同等重要性；2）在最终步骤将数据完全破坏为随机噪声；3）扩散步骤数足够充分。所提方法具有显著实用性，它通过离线计算数据集统计特征（可在训练前完成）的微小额外成本，消除了寻找最优噪声调度的需求。我们在跨领域数据集上通过时间序列预测、精细化及生成等多种任务验证了方法的有效性。代码已发布于：https://github.com/seunghan96/ANT。