UCL  IRIS
Institutional Research Information Service
UCL Logo
Please report any queries concerning the funding data grouped in the sections named "Externally Awarded" or "Internally Disbursed" (shown on the profile page) to your Research Finance Administrator. Your can find your Research Finance Administrator at https://www.ucl.ac.uk/finance/research/rs-contacts.php by entering your department
Please report any queries concerning the student data shown on the profile page to:

Email: portico-services@ucl.ac.uk

Help Desk: http://www.ucl.ac.uk/ras/portico/helpdesk
Publication Detail
A Scalable Laplace Approximation for Neural Networks
  • Publication Type:
    Conference
  • Authors:
    Ritter H, Botev A, Barber D
  • Publisher:
    International Conference on Representation Learning
  • Publication date:
    02/05/2018
  • Published proceedings:
    6th International Conference on Learning Representations, ICLR 2018 - Conference Track Proceedings
  • Status:
    Published
  • Name of conference:
    6th International Conference on Learning Representations (ICLR 2018)
  • Conference place:
    Vancouver, Canada
  • Conference start date:
    30/04/2018
  • Conference finish date:
    03/05/2018
Abstract
© Learning Representations, ICLR 2018 - Conference Track Proceedings.All right reserved. We leverage recent insights from second-order optimisation for neural networks to construct a Kronecker factored Laplace approximation to the posterior over the weights of a trained network. Our approximation requires no modification of the training procedure, enabling practitioners to estimate the uncertainty of their models currently used in production without having to retrain them. We extensively compare our method to using Dropout and a diagonal Laplace approximation for estimating the uncertainty of a network. We demonstrate that our Kronecker factored method leads to better uncertainty estimates on out-of-distribution data and is more robust to simple adversarial attacks. Our approach only requires calculating two square curvature factor matrices for each layer. Their size is equal to the respective square of the input and output size of the layer, making the method efficient both computationally and in terms of memory usage. We illustrate its scalability by applying it to a state-of-the-art convolutional network architecture.
Publication data is maintained in RPS. Visit https://rps.ucl.ac.uk
 More search options
UCL Researchers
Author
Dept of Computer Science
Author
Dept of Computer Science
University College London - Gower Street - London - WC1E 6BT Tel:+44 (0)20 7679 2000

© UCL 1999–2011

Search by