用于概率时间序列预测的循环插值体
Recurrent Interpolants for Probabilistic Time Series Prediction
AI总结：
针对现有序列模型难捕捉高维分布与跨特征依赖、生成式时间序列方法可扩展性不足的问题，本文提出结合循环神经网络效率与扩散模型概率建模能力的新方法，基于随机插值体和带控制特征的条件生成，为该领域发展提供思路。
摘要：
循环神经网络、Transformer等序列模型已成为各领域概率多变量时间序列预测的标准方法。尽管它们具备优势，但在捕捉高维分布与跨特征依赖关系方面存在困难。近期研究探索了基于扩散或流模型的生成式方法，并将其拓展至时间序列插补与预测任务，但可扩展性仍是一大挑战。本文提出一种新方法，基于随机插值体与带控制特征的条件生成，将循环神经网络的效率与扩散模型的概率建模能力相结合，为该动态领域的未来发展提供了思路。
英文摘要：
Sequential models like recurrent neural networks and transformers have become standard for probabilistic multivariate time series forecasting across various domains. Despite their strengths, they struggle with capturing high-dimensional distributions and cross-feature dependencies. Recent work explores generative approaches using diffusion or flow-based models, extending to time series imputation and forecasting. However, scalability remains a challenge. This work proposes a novel method combining recurrent neural networks' efficiency with diffusion models' probabilistic modeling, based on stochastic interpolants and conditional generation with control features, offering insights for future developments in this dynamic field.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
