English

Data-Driven Reachability analysis and Support set Estimation with Christoffel Functions

Systems and Control 2021-12-21 v1 Machine Learning Systems and Control

Abstract

We present algorithms for estimating the forward reachable set of a dynamical system using only a finite collection of independent and identically distributed samples. The produced estimate is the sublevel set of a function called an empirical inverse Christoffel function: empirical inverse Christoffel functions are known to provide good approximations to the support of probability distributions. In addition to reachability analysis, the same approach can be applied to general problems of estimating the support of a random variable, which has applications in data science towards detection of novelties and outliers in data sets. In applications where safety is a concern, having a guarantee of accuracy that holds on finite data sets is critical. In this paper, we prove such bounds for our algorithms under the Probably Approximately Correct (PAC) framework. In addition to applying classical Vapnik-Chervonenkis (VC) dimension bound arguments, we apply the PAC-Bayes theorem by leveraging a formal connection between kernelized empirical inverse Christoffel functions and Gaussian process regression models. The bound based on PAC-Bayes applies to a more general class of Christoffel functions than the VC dimension argument, and achieves greater sample efficiency in experiments.

Keywords

Cite

@article{arxiv.2112.09995,
  title  = {Data-Driven Reachability analysis and Support set Estimation with Christoffel Functions},
  author = {Alex Devonport and Forest Yang and Laurent El Ghaoui and Murat Arcak},
  journal= {arXiv preprint arXiv:2112.09995},
  year   = {2021}
}

Comments

20 pages, 3 figures. Submitted to the SIAM Journal on Control and Optimization. arXiv admin note: text overlap with arXiv:2104.13902

R2 v1 2026-06-24T08:23:13.552Z