{
  "id": "2103.02265",
  "version": "v1",
  "published": "2021-03-03T09:02:01.000Z",
  "updated": "2021-03-03T09:02:01.000Z",
  "title": "Meta-Learning with Variational Bayes",
  "authors": [
    "Lucas D. Lingle"
  ],
  "comment": "38 pages, 6 figures",
  "categories": [
    "cs.LG",
    "stat.ML"
  ],
  "abstract": "The field of meta-learning seeks to improve the ability of today's machine learning systems to adapt efficiently to small amounts of data. Typically this is accomplished by training a system with a parametrized update rule to improve a task-relevant objective based on supervision or a reward function. However, in many domains of practical interest, task data is unlabeled, or reward functions are unavailable. In this paper we introduce a new approach to address the more general problem of generative meta-learning, which we argue is an important prerequisite for obtaining human-level cognitive flexibility in artificial agents, and can benefit many practical applications along the way. Our contribution leverages the AEVB framework and mean-field variational Bayes, and creates fast-adapting latent-space generative models. At the heart of our contribution is a new result, showing that for a broad class of deep generative latent variable models, the relevant VB updates do not depend on any generative neural network.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2021-03-03T09:02:01.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "meta-learning",
      "deep generative latent variable models",
      "todays machine learning systems",
      "creates fast-adapting latent-space generative models",
      "relevant vb updates"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 38,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}