/SGMGT

Implementation for the paper "Stochastic Gradient Monomial Gamma Sampler"

Primary LanguagePython

SGMGT

Implementations of the models in the paper "Stochastic Gradient Monomial Gamma Sampler" by Yizhe Zhang, Changyou Chen, Zhe Gan, Ricardo Henao, Lawrence Carin, ICML 2017

Prerequisite:

  • Theono version >= 0.8
  • CUDA version 8.0
  • cudnn

Run

  • Run: python eval_ptb_sgmgt.py for demo
  • Options: options can be made by changing the model/optimizers.py code.

Data:

  • Penn Treebank dataset

For any question or suggestions, feel free to contact yz196@duke.edu

Citation

@InProceedings{zhang17astochastic,
  title = 	 {Stochastic Gradient Monomial Gamma Sampler},
  author = 	 {Yizhe Zhang and Changyou Chen and Zhe Gan and Ricardo Henao and Lawrence Carin},
  booktitle = 	 {Proceedings of the 34th International Conference on Machine Learning},
  pages = 	 {3996--4005},
  year = 	 {2017},
  publisher = {PMLR},
}