Meta-SysId: A Meta-Learning Approach for Simultaneous Identification and Prediction
Abstract
In this paper, we propose Meta-SysId, a meta-learning approach to model sets of systems that have behavior governed by common but unknown laws and that differentiate themselves by their context. Inspired by classical modeling-and-identification approaches, Meta-SysId learns to represent the common law through shared parameters and relies on online optimization to compute system-specific context. Compared to optimization-based meta-learning methods, the separation between class parameters and context variables reduces the computational burden while allowing batch computations and a simple training scheme. We test Meta-SysId on polynomial regression, time-series prediction, model-based control, and real-world traffic prediction domains, empirically finding it outperforms or is competitive with meta-learning baselines.
Cite
@article{arxiv.2206.00694,
title = {Meta-SysId: A Meta-Learning Approach for Simultaneous Identification and Prediction},
author = {Junyoung Park and Federico Berto and Arec Jamgochian and Mykel J. Kochenderfer and Jinkyoo Park},
journal= {arXiv preprint arXiv:2206.00694},
year = {2022}
}
Comments
9 pages, 8 figures