{
  "id": "2206.00694",
  "version": "v1",
  "published": "2022-06-01T18:04:22.000Z",
  "updated": "2022-06-01T18:04:22.000Z",
  "title": "Meta-SysId: A Meta-Learning Approach for Simultaneous Identification and Prediction",
  "authors": [
    "Junyoung Park",
    "Federico Berto",
    "Arec Jamgochian",
    "Mykel J. Kochenderfer",
    "Jinkyoo Park"
  ],
  "comment": "9 pages, 8 figures",
  "categories": [
    "cs.LG"
  ],
  "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.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2022-06-01T18:04:22.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "meta-learning approach",
      "simultaneous identification",
      "real-world traffic prediction domains",
      "context variables reduces",
      "modeling-and-identification approaches"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 9,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}