• Stars
    star
    180
  • Rank 213,097 (Top 5 %)
  • Language
    Python
  • License
    GNU General Publi...
  • Created almost 5 years ago
  • Updated 3 months ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Stochastic Automatic Differentiation library for PyTorch.

General Stochastic Automatic Differentiation for Pytorch

Documentation Status

Storchastic is a PyTorch library for stochastic gradient estimation in Deep Learning [1]. Many state of the art deep learning models use gradient estimation, in particular within the fields of Variational Inference and Reinforcement Learning. While PyTorch computes gradients of deterministic computation graphs automatically, it will not estimate gradients on stochastic computation graphs [2].

With Storchastic, you can easily define any stochastic deep learning model and let it estimate the gradients for you. Storchastic provides a large range of gradient estimation methods that you can plug and play, to figure out which one works best for your problem. Storchastic provides automatic broadcasting of sampled batch dimensions, which increases code readability and allows implementing complex models with ease.

When dealing with continuous random variables and differentiable functions, the popular reparameterization method [3] is usually very effective. However, this method is not applicable when dealing with discrete random variables or non-differentiable functions. This is why Storchastic has a focus on gradient estimators for discrete random variables, non-differentiable functions and sequence models.

Documentation on Read the Docs.

Example: Discrete Variational Auto-Encoder

Installation

In your virtual Python environment, run pip install storchastic

Requires Pytorch 1.8 and Pyro. The code is build using Python 3.8.

Algorithms

Feel free to create an issue if an estimator is missing here.

  • Reparameterization [1, 3]
  • Score Function (REINFORCE) with Moving Average baseline [1, 4]
  • Score Function with Batch Average Baseline [5, 6]
  • Expected value for enumerable distributions
  • (Straight through) Gumbel Softmax [7, 8]
  • LAX, RELAX [9]
  • REBAR [10]
  • REINFORCE Without Replacement [6]
  • Unordered Set Estimator [13]
  • ARM [15]
  • Rao-Blackwellized REINFORCE [12]

In development

  • Memory Augmented Policy Optimization [11]

Planned

  • Measure valued derivatives [1, 14]
  • Automatic Credit Assignment [16]
  • ...

References

Cite

To cite Storchastic, please cite this preprint:

@article{van2021storchastic,
  title={Storchastic: A Framework for General Stochastic Automatic Differentiation},
  author={van Krieken, Emile and Tomczak, Jakub M and Teije, Annette ten},
  journal={arXiv preprint arXiv:2104.00428},
  year={2021}
}