Skip to content

thiagopbueno/gradient-estimators-in-stochastic-computation-graphs

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

14 Commits
 
 
 
 
 
 
 
 

Repository files navigation

gradient-estimators-in-stochastic-computation-graphs

Gradient Estimation in Stochastic Computation Graphs using TensorFlow.

In this IPython notebook, we aim at exploring different ways to estimate gradients in stochastic computation graphs in order to optimize an objective function defined by an expectation over a set of random variables.

In terms of implementation, we'll use the TensorFlow library, mainly because of its automatic reverse-mode differentiation capabilities.

The notation and theory are based on the following NIPS paper:

Schulman, J., Heess, N., Weber, T. and Abbeel, P., 2015.
Gradient estimation using stochastic computation graphs. In Advances in Neural Information Processing Systems (pp. 3528-3536).

About

Gradient Estimation in Stochastic Computation Graphs using TensorFlow.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published