Learning of Linear Dynamical Systems as a Non-Commutative Polynomial Optimization Problem

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Quan, Marecek, Jakub
Format: Preprint
Published: 2020
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909120464945152
author Zhou, Quan
Marecek, Jakub
author_facet Zhou, Quan
Marecek, Jakub
contents There has been much recent progress in forecasting the next observation of a linear dynamical system (LDS), which is known as the improper learning, as well as in the estimation of its system matrices, which is known as the proper learning of LDS. We present an approach to proper learning of LDS, which in spite of the non-convexity of the problem, guarantees global convergence of numerical solutions to a least-squares estimator. We present promising computational results.
format Preprint
id arxiv_https___arxiv_org_abs_2002_01444
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Learning of Linear Dynamical Systems as a Non-Commutative Polynomial Optimization Problem
Zhou, Quan
Marecek, Jakub
Optimization and Control
Machine Learning
Systems and Control
There has been much recent progress in forecasting the next observation of a linear dynamical system (LDS), which is known as the improper learning, as well as in the estimation of its system matrices, which is known as the proper learning of LDS. We present an approach to proper learning of LDS, which in spite of the non-convexity of the problem, guarantees global convergence of numerical solutions to a least-squares estimator. We present promising computational results.
title Learning of Linear Dynamical Systems as a Non-Commutative Polynomial Optimization Problem
topic Optimization and Control
Machine Learning
Systems and Control
url https://arxiv.org/abs/2002.01444