ANT: Adaptive Noise Schedule for Time Series Diffusion Models

TL;DR

This paper introduces ANT, an adaptive noise scheduling method for time series diffusion models that automatically determines optimal noise schedules based on data statistics, improving performance across multiple tasks.

Contribution

ANT is a novel method that automatically adapts noise schedules for time series diffusion models considering data non-stationarity, reducing manual tuning and enhancing performance.

Findings

Improved performance on TS forecasting, refinement, and generation tasks.

Effective automatic noise schedule determination with minimal additional computation.

Validated across diverse datasets and domains.

Abstract

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.