Finite sample learning of moving targets

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.

@article{vertovec2025_2408.04406,
  title={ Finite sample learning of moving targets },
  author={ Nikolaus Vertovec and Kostas Margellos and Maria Prandini },
  journal={arXiv preprint arXiv:2408.04406},
  year={ 2025 }
}