Meta-Learning for Koopman Spectral Analysis with Short Time-series
NTT Communication Science Laboratories, NTT Corporation（NTT公司NTT通信科学实验室）；Institute of Mathematics for Industry, Kyushu University（九州大学产业数学研究所）；Center for Advanced Intelligence Project, RIKEN（理化学研究所高级智能项目中心）
Koopman spectral analysis has attracted attention for nonlinear dynamical systems since we can analyze nonlinear dynamics with a linear regime by embedding data into a Koopman space by a nonlinear function. For the analysis, we need to find appropriate embedding functions. Although several neural network-based methods have been proposed for learning embedding functions, existing methods require long time-series for training neural networks. This limitation prohibits performing Koopman spectral analysis in applications where only short time-series are available. In this paper, we propose a meta-learning method for estimating embedding functions from unseen short time-series by exploiting knowledge learned from related but different time-series. With the proposed method, a representation of a given short time-series is obtained by a bidirectional LSTM for extracting its properties. The embedding function of the short time-series is modeled by a neural network that depends on the time-series representation. By sharing the LSTM and neural networks across multiple time-series, we can learn common knowledge from different time-series while modeling time-series-specific embedding functions with the time-series representation. Our model is trained such that the expected test prediction error is minimized with the episodic training framework. We experimentally demonstrate that the proposed method achieves better performance in terms of eigenvalue estimation and future prediction than existing methods.
SKOLR: Structured Koopman Operator Linear RNN for Time-Series Forecasting
Department of Electrical and Computer Engineering, McGill University, Montreal, Canada（麦吉尔大学电气与计算机工程系）；Amazon Science. This work does not relate to the author’s position at Amazon（亚马逊科学）；Mila - Quebec Artificial Intelligence Institute, Montreal, Canada（魁北克人工智能研究所）；ILLS - International Laboratory on Learning Systems, Montreal, Canada（学习系统国际实验室）
MAKO: Meta-Adaptive Koopman Operators for Learning-based Model Predictive Control of Parametrically Uncertain Nonlinear Systems
Water Research Institute (NEWRI), Nanyang Technological University, Singapore（新跃大学水研究 institute（NEWRI））；School of Chemistry, Chemical Engineering and Biotechnology, Nanyang Technological University, Singapore（新跃大学化学、化工与生物技术学院）；Soft Robotics Lab, ETH Zurich, Switzerland（苏黎世联邦理工学院软机器人实验室）；Department of Civil and Environmental Engineering, National University of Singapore, Singapore（新加坡国立大学土木与环境工程系）
Neural Dynamic Mode Decomposition for End-to-End Modeling of Nonlinear Dynamics
NTT Communication Science Laboratories（NTT通信科学实验室）；Institute of Mathematics for Industry, Kyushu University（九州大学产业数学研究所）；Center for Advanced Intelligence Project, RIKEN（理化学研究所先进智能项目中心）
Tailored Forecasting from Short Time Series via Meta-learning
University of Maryland（马里兰大学）；Institute for Research in Electronics and Applied Physics（电子与应用物理研究所）；Department of Electrical and Computer Engineering（电气与计算机工程系）；Potomac Research LLC（波托马克研究公司）；Institute for Physical Science and Technology（物理科学与技术研究所）；Santa Fe Institute（圣菲研究所）
MetaCaster: Meta-Harness-Optimized Agent for End-to-End Few-Shot Learning of Lightweight Time Series Forecasters
University of Houston（休斯顿大学）；NEC Labs（NEC实验室）；University of Waterloo（滑铁卢大学）；University of Connecticut（康涅狄格大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Singapore Management University（新加坡管理大学）
Multi-task Meta Label Correction for Time Series Prediction
Huazhong University of Science and Technology（华中科技大学）；Shanghai Jiao Tong University（上海交通大学）；Wuhan University of Technology（武汉理工大学）；Great Bay University（大湾区大学）
