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

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

URL: http://arxiv.org/abs/2112.09995v1
Date: Sat, 18 Dec 2021 20:25:34 GMT
Title: Data-Driven Reachability analysis and Support set Estimation with Christoffel Functions
Authors: Alex Devonport, Forest Yang, Laurent El Ghaoui, and Murat Arcak
Abstract summary: We present algorithms for estimating the forward reachable set of a dynamical system. The produced estimate is the sublevel set of a function called an empirical inverse Christoffel function. In addition to reachability analysis, the same approach can be applied to general problems of estimating the support of a random variable.
Score: 8.183446952097528
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
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.