{
  "id": "2207.03804",
  "version": "v1",
  "published": "2022-07-08T10:19:15.000Z",
  "updated": "2022-07-08T10:19:15.000Z",
  "title": "On the Subspace Structure of Gradient-Based Meta-Learning",
  "authors": [
    "Gustaf Tegnér",
    "Alfredo Reichlin",
    "Hang Yin",
    "Mårten Björkman",
    "Danica Kragic"
  ],
  "categories": [
    "cs.LG"
  ],
  "abstract": "In this work we provide an analysis of the distribution of the post-adaptation parameters of Gradient-Based Meta-Learning (GBML) methods. Previous work has noticed how, for the case of image-classification, this adaption only takes place on the last layers of the network. We propose the more general notion that parameters are updated over a low-dimensional \\emph{subspace} of the same dimensionality as the task-space and show that this holds for regression as well. Furthermore, the induced subspace structure provides a method to estimate the intrinsic dimension of the space of tasks of common few-shot learning datasets.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2022-07-08T10:19:15.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "gradient-based meta-learning",
      "common few-shot learning datasets",
      "induced subspace structure",
      "intrinsic dimension",
      "post-adaptation parameters"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}