arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.07834cs.LG
收藏

使用 Koopman 算子跨时间域泛化

Generalizing across Temporal Domains with Koopman Operators

The University of Western Ontario(西安大略大学);Beihang University(北京航空航天大学);Vector Institute(矢量研究所)

Qiuhao Zeng, Wei Wang, Fan Zhou, Gezheng Xu, Ruizhi Pu, Changjian Shui, Christian Gagne, Shichun Yang, Boyu Wang, Charles X. Ling

AI总结:

针对时间域泛化问题,本文提出基于 Koopman 神经算子的时间 Koopman 网络(TKNets),通过寻找测量函数建立演化域间的线性转换关系以处理时间演化分布,并从理论上证明对齐条件分布能减小泛化误差界。

摘要:

在领域泛化领域,构建能够在无法访问目标域数据的情况下泛化到目标域的预测模型仍然是一项具有挑战性的任务。当考虑到领域之间不断演化的动态特性时,这个问题变得更加复杂。尽管已经提出了各种方法来解决这个问题,但对潜在的泛化理论仍然缺乏全面的理解。在本研究中,我们贡献了新的理论结果,即对齐条件分布会导致泛化误差界的减小。我们的分析作为通过应用 Koopman 神经算子来解决时间域泛化(TDG)问题的关键动机,从而提出了时间 Koopman 网络(TKNets)。通过采用 Koopman 算子,我们利用 Koopman 理论的原则有效地解决了 TDG 中遇到的时间演化分布问题,其中寻找测量函数以在不断演化的领域之间建立线性转换关系。通过在合成和真实世界数据集上进行的实证评估,我们验证了所提出方法的有效性。

英文摘要:

In the field of domain generalization, the task of constructing a predictive model capable of generalizing to a target domain without access to target data remains challenging. This problem becomes further complicated when considering evolving dynamics between domains. While various approaches have been proposed to address this issue, a comprehensive understanding of the underlying generalization theory is still lacking. In this study, we contribute novel theoretic results that aligning conditional distribution leads to the reduction of generalization bounds. Our analysis serves as a key motivation for solving the Temporal Domain Generalization (TDG) problem through the application of Koopman Neural Operators, resulting in Temporal Koopman Networks (TKNets). By employing Koopman Operators, we effectively address the time-evolving distributions encountered in TDG using the principles of Koopman theory, where measurement functions are sought to establish linear transition relations between evolving domains. Through empirical evaluations conducted on synthetic and real-world datasets, we validate the effectiveness of our proposed approach.

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。

↑