自回归模型
初始化
星型
计算机科学
系列(地层学)
时间序列
SETAR公司
自回归滑动平均模型
非线性自回归外生模型
自回归积分移动平均
人工智能
机器学习
计量经济学
数学
古生物学
生物
程序设计语言
作者
Lifeng Shen,James Tin-Yau Kwok
标识
DOI:10.48550/arxiv.2306.05043
摘要
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).
科研通智能强力驱动
Strongly Powered by AbleSci AI