Maximum entropy estimation via Gauss-LP quadratures

Conference paper (2017)

Authors

Maxime Thély ETH Zürich
Tobias Sutter ETH Zürich
P. Mohajerin Esfahani Team Tamas Keviczky - Mechanical, Maritime and Materials Engineering
John Lygeros ETH Zürich
Research Group
Team Bart De Schutter (Mechanical, Maritime and Materials Engineering) (TU Delft)
Copyright: © 2017 Maxime Thély, Tobias Sutter, P. Mohajerin Esfahani, John Lygeros
DOI: https://doi.org/10.1016/j.ifacol.2017.08.1977
More Info
expand_more

Published Date

2017

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Mechanical, Maritime and Materials Engineering

Department

Delft Center for Systems and Control

Research Group

Team Bart De Schutter

Abstract

We present an approximation method to a class of parametric integration problems that naturally appear when solving the dual of the maximum entropy estimation problem. Our method builds up on a recent generalization of Gauss quadratures via an infinite-dimensional linear program, and utilizes a convex clustering algorithm to compute an approximate solution which requires reduced computational effort. It shows to be particularly appealing when looking at problems with unusual domains and in a multi-dimensional setting. As a proof of concept we apply our method to an example problem on the unit disc.