Generalizing across Temporal Domains with Koopman Operators
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916126801264640 |
|---|---|
| author | Zeng, Qiuhao Wang, Wei Zhou, Fan Xu, Gezheng Pu, Ruizhi Shui, Changjian Gagne, Christian Yang, Shichun Wang, Boyu Ling, Charles X. |
| author_facet | Zeng, Qiuhao Wang, Wei Zhou, Fan Xu, Gezheng Pu, Ruizhi Shui, Changjian Gagne, Christian Yang, Shichun Wang, Boyu Ling, Charles X. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_07834 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Generalizing across Temporal Domains with Koopman Operators Zeng, Qiuhao Wang, Wei Zhou, Fan Xu, Gezheng Pu, Ruizhi Shui, Changjian Gagne, Christian Yang, Shichun Wang, Boyu Ling, Charles X. Machine Learning 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. |
| title | Generalizing across Temporal Domains with Koopman Operators |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2402.07834 |