Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2311.00875 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911828275101696 |
|---|---|
| author | Feng, Jinchao Zhong, Ming |
| author_facet | Feng, Jinchao Zhong, Ming |
| contents | We present a comprehensive examination of learning methodologies employed for the structural identification of dynamical systems. These techniques are designed to elucidate emergent phenomena within intricate systems of interacting agents. Our approach not only ensures theoretical convergence guarantees but also exhibits computational efficiency when handling high-dimensional observational data. The methods adeptly reconstruct both first- and second-order dynamical systems, accommodating observation and stochastic noise, intricate interaction rules, absent interaction features, and real-world observations in agent systems. The foundational aspect of our learning methodologies resides in the formulation of tailored loss functions using the variational inverse problem approach, inherently equipping our methods with dimension reduction capabilities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_00875 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Learning Collective Behaviors from Observation Feng, Jinchao Zhong, Ming Machine Learning Multiagent Systems Dynamical Systems We present a comprehensive examination of learning methodologies employed for the structural identification of dynamical systems. These techniques are designed to elucidate emergent phenomena within intricate systems of interacting agents. Our approach not only ensures theoretical convergence guarantees but also exhibits computational efficiency when handling high-dimensional observational data. The methods adeptly reconstruct both first- and second-order dynamical systems, accommodating observation and stochastic noise, intricate interaction rules, absent interaction features, and real-world observations in agent systems. The foundational aspect of our learning methodologies resides in the formulation of tailored loss functions using the variational inverse problem approach, inherently equipping our methods with dimension reduction capabilities. |
| title | Learning Collective Behaviors from Observation |
| topic | Machine Learning Multiagent Systems Dynamical Systems |
| url | https://arxiv.org/abs/2311.00875 |