Institute Homepage
Institute Homepage DE Sign In

Back

Empirical Inference Probabilistic Numerics Conference Paper 2019

Limitations of the empirical Fisher approximation for natural gradient descent

no image
Probabilistic Numerics
Frederik Künstner
Thumb ticker sm hennig lowres cropped
Probabilistic Numerics, Empirical Inference
Philipp Hennig
Affiliated Researcher
Thumb ticker sm profile 1
Probabilistic Numerics
Lukas Balles

Author(s): Kunstner, F. and Hennig, P. and Balles, L.
Book Title: Advances in Neural Information Processing Systems 32 (NeurIPS 2019)
Pages: 4158--4169
Year: 2019
Month: December
Editors: H. Wallach and H. Larochelle and A. Beygelzimer and F. d'Alch\'{e}-Buc and E. Fox and R. Garnett
Publisher: Curran Associates, Inc.
Bibtex Type: Conference Paper (conference)
Event Name: 33rd Annual Conference on Neural Information Processing Systems
Event Place: Vancouver, Canada
State: Published
URL: https://papers.nips.cc/paper/8669-limitations-of-the-empirical-fisher-approximation-for-natural-gradient-descent
Electronic Archiving: grant_archive

BibTex 

@conference{KunHenBal19,
  title = {Limitations of the empirical Fisher approximation for natural gradient descent},
  booktitle = {Advances in Neural Information Processing Systems 32 (NeurIPS 2019)},
  pages = {4158--4169},
  editors = {H. Wallach and H. Larochelle and A. Beygelzimer and F. d'Alch\'{e}-Buc and E. Fox and R. Garnett},
  publisher = {Curran Associates, Inc.},
  month = dec,
  year = {2019},
  slug = {kunhenbal19},
  author = {Kunstner, F. and Hennig, P. and Balles, L.},
  url = {https://papers.nips.cc/paper/8669-limitations-of-the-empirical-fisher-approximation-for-natural-gradient-descent},
  month_numeric = {12}
}