Learning Multiple Nonlinear Dynamical Systems with Side Information

Naoya Takeishi, Yoshinobu Kawahara

研究成果: 書籍/レポート タイプへの寄稿会議への寄与

抄録

We address the problem of learning multiple dynamical systems, which is a kind of multi-task learning (MTL). The existing methods of MTL do not apply to learning dynamical systems in general. In this work, we develop a regularization method to perform MTL for dynamical systems appropriately. The proposed method is based on an operator-theoretic metric on dynamics that is agnostic of model parametrization and applicable even for nonlinear dynamics models. We calculate the proposed MTL-like regularization by estimating the metric from trajectories generated during training. Learning time varying systems can be regarded as a special case of the usage of the proposed method. The proposed regularizer is versatile as we can straightforwardly incorporate it into off the-shelf gradient-based optimization methods. We show the results of experiments on synthetic and real-world datasets, which exhibits the validity of the proposed regularizer.

本文言語英語
ホスト出版物のタイトル2020 59th IEEE Conference on Decision and Control, CDC 2020
出版社Institute of Electrical and Electronics Engineers Inc.
ページ3206-3211
ページ数6
ISBN(電子版)9781728174471
DOI
出版ステータス出版済み - 12月 14 2020
イベント59th IEEE Conference on Decision and Control, CDC 2020 - Virtual, Jeju Island, 韓国
継続期間: 12月 14 202012月 18 2020

出版物シリーズ

名前Proceedings of the IEEE Conference on Decision and Control
2020-December
ISSN(印刷版)0743-1546
ISSN(電子版)2576-2370

会議

会議59th IEEE Conference on Decision and Control, CDC 2020
国/地域韓国
CityVirtual, Jeju Island
Period12/14/2012/18/20

!!!All Science Journal Classification (ASJC) codes

  • 制御およびシステム工学
  • モデリングとシミュレーション
  • 制御と最適化

フィンガープリント

「Learning Multiple Nonlinear Dynamical Systems with Side Information」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル