Finite sample learning of moving targets
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912696614518784 |
|---|---|
| author | Vertovec, Nikolaus Margellos, Kostas Prandini, Maria |
| author_facet | Vertovec, Nikolaus Margellos, Kostas Prandini, Maria |
| contents | We consider a moving target that we seek to learn from samples. Our results extend randomized techniques developed in control and optimization for a constant target to the case where the target is changing. We derive a novel bound on the number of samples that are required to construct a probably approximately correct (PAC) estimate of the target. Furthermore, when the moving target is a convex polytope, we provide a constructive method of generating the PAC estimate using a mixed integer linear program (MILP). The proposed method is demonstrated on an application to autonomous emergency braking. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_04406 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Finite sample learning of moving targets Vertovec, Nikolaus Margellos, Kostas Prandini, Maria Optimization and Control Machine Learning We consider a moving target that we seek to learn from samples. Our results extend randomized techniques developed in control and optimization for a constant target to the case where the target is changing. We derive a novel bound on the number of samples that are required to construct a probably approximately correct (PAC) estimate of the target. Furthermore, when the moving target is a convex polytope, we provide a constructive method of generating the PAC estimate using a mixed integer linear program (MILP). The proposed method is demonstrated on an application to autonomous emergency braking. |
| title | Finite sample learning of moving targets |
| topic | Optimization and Control Machine Learning |
| url | https://arxiv.org/abs/2408.04406 |