用薛定谔桥生成时间序列，能更好捕捉复杂动态。
Robust time series generation via Schrödinger Bridge: a comprehensive evaluation
- 将时间序列生成建模为路径空间上的熵最优传输问题
- 在多个数据集上优于或媲美当前最优生成方法
- 适合需要高鲁棒性与动态建模能力的时序任务
我们研究了薛定谔桥（Schrödinger Bridge, SB）方法在时间序列生成中的表现。该框架将时间序列合成建模为路径空间上参考分布与目标联合分布间的熵最优插值传输问题，由此导出一个有限时域的随机微分方程，能准确捕捉目标时间序列的时序动态。尽管SB在图像生成等领域已有广泛探索，但其在时间序列领域的应用仍较少。本文通过在多样化数据集上对SB方法进行全面评估，对比当前最先进的时间序列生成方法，考察其鲁棒性、生成性能及建模复杂时序依赖的能力。结果表明，SB框架具备作为通用且稳健的时间序列生成工具的巨大潜力。
原文摘要 · Abstract (English)
We investigate the generative capabilities of the Schrödinger Bridge (SB) approach for time series. The SB framework formulates time series synthesis as an entropic optimal interpolation transport problem between a reference probability measure on path space and a target joint distribution. This results in a stochastic differential equation over a finite horizon that accurately captures the temporal dynamics of the target time series. While the SB approach has been largely explored in fields like image generation, there is a scarcity of studies for its application to time series. In this work, we bridge this gap by conducting a comprehensive evaluation of the SB method's robustness and generative performance. We benchmark it against state-of-the-art (SOTA) time series generation methods across diverse datasets, assessing its strengths, limitations, and capacity to model complex temporal dependencies. Our results offer valuable insights into the SB framework's potential as a versatile and robust tool for time series generation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。