The code for Meta Learning for SGMCMC
Switch branches/tags
Nothing to show
Clone or download
WenboGong Meta Sampler and corresponding Training files:
  Implement Optimizer Test File
Latest commit d236c38 Sep 24, 2018

README.md

Meta-Learning with Stochastic Gradient MCMC

This repo contains the implementation of the experiments in the following paper:

Wenbo Gong*, Yingzhen Li* and Jose Miguel Hernandez Lobato

Meta-Learning for Stochastic Gradient MCMC

ArXiv 1806.04522

Contributions: Wenbo and Yingzhen initiated the project together. Wenbo designed the architecture of the sampler, and implemented all the experiments. Yingzhen is mainly responsible for loss function design, experiment design, and the paper writing. Miguel is here because he is Wenbo's PhD supervisor, and he provided some comments on the draft.

We will be releasing all the implementations very shortly. If you use it in your research, please consider citing the paper.

Gaussian experiments

See README in Toy Example/

MNIST experiments

See README in BNN_MNIST/

Citing the paper (bib)

@article{gong2018meta,
  title = {Meta-Learning for Stochastic Gradient MCMC},
  author = {Gong, Wenbo and Li, Yingzhen and Hern\'andez-Lobato, Jos\'e Miguel},
  journal={arXiv preprint arXiv:1806.04522},
  year={2018}
}