Universal Approximation of Dynamical Systems by Semi-Autonomous Neural ODEs and Applications
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917195262459904 |
|---|---|
| author | Li, Ziqian Liu, Kang Liverani, Lorenzo Zuazua, Enrique |
| author_facet | Li, Ziqian Liu, Kang Liverani, Lorenzo Zuazua, Enrique |
| contents | In this paper, we introduce semi-autonomous neural ordinary differential equations (SA-NODEs), a variation of the vanilla NODEs, employing fewer parameters. We investigate the universal approximation properties of SA-NODEs for dynamical systems from both a theoretical and a numerical perspective. Within the assumption of a finite-time horizon, under general hypotheses we establish an asymptotic approximation result, demonstrating that the error vanishes as the number of parameters goes to infinity. Under additional regularity assumptions, we further specify this convergence rate in relation to the number of parameters, utilizing quantitative approximation results in the Barron space. Based on the previous result, we prove an approximation rate for transport equations by their neural counterparts. Our numerical experiments validate the effectiveness of SA-NODEs in capturing the dynamics of various ODE systems and transport equations. Additionally, we compare SA-NODEs with vanilla NODEs, highlighting the superior performance and reduced complexity of our approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_17092 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Universal Approximation of Dynamical Systems by Semi-Autonomous Neural ODEs and Applications Li, Ziqian Liu, Kang Liverani, Lorenzo Zuazua, Enrique Numerical Analysis 34A45, 41A25, 65D15, 65L09, 68T07 In this paper, we introduce semi-autonomous neural ordinary differential equations (SA-NODEs), a variation of the vanilla NODEs, employing fewer parameters. We investigate the universal approximation properties of SA-NODEs for dynamical systems from both a theoretical and a numerical perspective. Within the assumption of a finite-time horizon, under general hypotheses we establish an asymptotic approximation result, demonstrating that the error vanishes as the number of parameters goes to infinity. Under additional regularity assumptions, we further specify this convergence rate in relation to the number of parameters, utilizing quantitative approximation results in the Barron space. Based on the previous result, we prove an approximation rate for transport equations by their neural counterparts. Our numerical experiments validate the effectiveness of SA-NODEs in capturing the dynamics of various ODE systems and transport equations. Additionally, we compare SA-NODEs with vanilla NODEs, highlighting the superior performance and reduced complexity of our approach. |
| title | Universal Approximation of Dynamical Systems by Semi-Autonomous Neural ODEs and Applications |
| topic | Numerical Analysis 34A45, 41A25, 65D15, 65L09, 68T07 |
| url | https://arxiv.org/abs/2407.17092 |