Recently, denoising diffusion models have led to significant breakthroughs in
the generation of images, audio and text. However, it is still an open question
on how to adapt their strong modeling ability to model time series. In this
paper, we propose TimeDiff, a non-autoregressive diffusion model that achieves
high-quality time series prediction with the introduction of two novel
conditioning mechanisms: future mixup and autoregressive initialization.
Similar to teacher forcing, future mixup allows parts of the ground-truth
future predictions for conditioning, while autoregressive initialization helps
better initialize the model with basic time series patterns such as short-term
trends. Extensive experiments are performed on nine real-world datasets.
Results show that TimeDiff consistently outperforms existing time series
diffusion models, and also achieves the best overall performance across a
variety of the existing strong baselines (including transformers and FiLM).

本文提出了一种基于 non-autoregressive diffusion model 的时间序列预测模型 TimeDiff，通过引入 future mixup 和 autoregressive initialization 两种新的条件机制，实现了高质量的时间序列预测，并在实验中展现了超过现有模型的表现。