A comparison study of supervised learning techniques for the approximation of high dimensional functions and feedback control
Numerical Analysis
2024-02-05 v1 Numerical Analysis
Optimization and Control
Abstract
Approximation of high dimensional functions is in the focus of machine learning and data-based scientific computing. In many applications, empirical risk minimisation techniques over nonlinear model classes are employed. Neural networks, kernel methods and tensor decomposition techniques are among the most popular model classes. We provide a numerical study comparing the performance of these methods on various high-dimensional functions with focus on optimal control problems, where the collection of the dataset is based on the application of the State-Dependent Riccati Equation.
Cite
@article{arxiv.2402.01402,
title = {A comparison study of supervised learning techniques for the approximation of high dimensional functions and feedback control},
author = {Mathias Oster and Luca Saluzzi and Tizian Wenzel},
journal= {arXiv preprint arXiv:2402.01402},
year = {2024}
}