Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2409.11141 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915043463921664 |
|---|---|
| author | Chatzikiriakos, Nicolas Iannelli, Andrea |
| author_facet | Chatzikiriakos, Nicolas Iannelli, Andrea |
| contents | This paper considers a finite sample perspective on the problem of identifying an LTI system from a finite set of possible systems using trajectory data. To this end, we use the maximum likelihood estimator to identify the true system and provide an upper bound for its sample complexity. Crucially, the derived bound does not rely on a potentially restrictive stability assumption. Additionally, we leverage tools from information theory to provide a lower bound to the sample complexity that holds independently of the used estimator. The derived sample complexity bounds are analyzed analytically and numerically. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_11141 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Sample Complexity Bounds for Linear System Identification from a Finite Set Chatzikiriakos, Nicolas Iannelli, Andrea Systems and Control Machine Learning This paper considers a finite sample perspective on the problem of identifying an LTI system from a finite set of possible systems using trajectory data. To this end, we use the maximum likelihood estimator to identify the true system and provide an upper bound for its sample complexity. Crucially, the derived bound does not rely on a potentially restrictive stability assumption. Additionally, we leverage tools from information theory to provide a lower bound to the sample complexity that holds independently of the used estimator. The derived sample complexity bounds are analyzed analytically and numerically. |
| title | Sample Complexity Bounds for Linear System Identification from a Finite Set |
| topic | Systems and Control Machine Learning |
| url | https://arxiv.org/abs/2409.11141 |