Importance Sampling for Statistical Certification of Viable Initial Sets

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Dietrich, Elizabeth, Krasowski, Hanna, Flovik, Vegard, Arcak, Murat
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915912835137536
author Dietrich, Elizabeth
Krasowski, Hanna
Flovik, Vegard
Arcak, Murat
author_facet Dietrich, Elizabeth
Krasowski, Hanna
Flovik, Vegard
Arcak, Murat
contents We study the problem of statistically certifying viable initial sets (VISs) -- sets of initial conditions whose trajectories satisfy a given control specification. While VISs can be obtained from model-based methods, these methods typically rely on simplified models. We propose a simulation-based framework to certify VISs by estimating the probability of specification violations under a high-fidelity or black-box model. Since detecting these violations may be challenging due to their scarcity, we propose a sample-efficient framework that leverages importance sampling to target high-risk regions. We derive an empirical Bernstein inequality for weighted random variables, enabling finite-sample guarantees for importance sampling estimators. We demonstrate the effectiveness of the proposed approach on two systems and show improved convergence of the resulting bounds on an Adaptive Cruise Control benchmark.
format Preprint
id arxiv_https___arxiv_org_abs_2604_02939
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Importance Sampling for Statistical Certification of Viable Initial Sets
Dietrich, Elizabeth
Krasowski, Hanna
Flovik, Vegard
Arcak, Murat
Systems and Control
We study the problem of statistically certifying viable initial sets (VISs) -- sets of initial conditions whose trajectories satisfy a given control specification. While VISs can be obtained from model-based methods, these methods typically rely on simplified models. We propose a simulation-based framework to certify VISs by estimating the probability of specification violations under a high-fidelity or black-box model. Since detecting these violations may be challenging due to their scarcity, we propose a sample-efficient framework that leverages importance sampling to target high-risk regions. We derive an empirical Bernstein inequality for weighted random variables, enabling finite-sample guarantees for importance sampling estimators. We demonstrate the effectiveness of the proposed approach on two systems and show improved convergence of the resulting bounds on an Adaptive Cruise Control benchmark.
title Importance Sampling for Statistical Certification of Viable Initial Sets
topic Systems and Control
url https://arxiv.org/abs/2604.02939