{
  "id": "2103.00222",
  "version": "v1",
  "published": "2021-02-27T14:06:29.000Z",
  "updated": "2021-02-27T14:06:29.000Z",
  "title": "Variational Laplace for Bayesian neural networks",
  "authors": [
    "Ali Unlu",
    "Laurence Aitchison"
  ],
  "categories": [
    "stat.ML",
    "cs.LG"
  ],
  "abstract": "We develop variational Laplace for Bayesian neural networks (BNNs) which exploits a local approximation of the curvature of the likelihood to estimate the ELBO without the need for stochastic sampling of the neural-network weights. Variational Laplace performs better on image classification tasks than MAP inference and far better than standard variational inference with stochastic sampling despite using the same mean-field Gaussian approximate posterior. The Variational Laplace objective is simple to evaluate, as it is (in essence) the log-likelihood, plus weight-decay, plus a squared-gradient regularizer. Finally, we emphasise care needed in benchmarking standard VI as there is a risk of stopping before the variance parameters have converged. We show that early-stopping can be avoided by increasing the learning rate for the variance parameters.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2021-02-27T14:06:29.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "bayesian neural networks",
      "variance parameters",
      "variational laplace performs better",
      "mean-field gaussian approximate posterior",
      "image classification tasks"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}