SLANG: Fast Structured Covariance Approximations for Bayesian Deep Learning with Natural Gradient

Code for reproducing the experimental results in the paper SLANG: Fast Structured Covariance Approximations for Bayesian Deep Learning with Natural Gradient by Aaron Mishkin, Frederik Kunstner, Didrik Nielsen, Mark Schmidt, and Mohammad Emtiyaz Khan.

See the code folder for installation instructions.

---

@inproceedings{mishkin2018slang,
  author    = {Aaron Mishkin and Frederik Kunstner and Didrik Nielsen and Mark W. Schmidt and Mohammad Emtiyaz Khan},
  editor    = {Samy Bengio and Hanna M. Wallach and Hugo Larochelle and Kristen Grauman and Nicol{\`{o}} Cesa{-}Bianchi and Roman Garnett},
  title     = {{SLANG:} Fast Structured Covariance Approximations for {B}ayesian Deep Learning with Natural Gradient},
  booktitle = {Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, 3-8 December 2018, Montr{\'{e}}al, Canada.},
  pages     = {6248--6258},
  year      = {2018},
}