Skip to content

thangbui/var-gp

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

54 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Continual Learning with GPs

This repository hosts code for Variational Auto-Regressive Gaussian Processes for Continual Learning by Sanyam Kapoor, Theofanis Karaletsos, Thang D. Bui.

Setup

From the root of the directory

conda env create

This creates the environment from environment.yml.

In addition, ensure availability of the this directory in PYTHONPATH for module imports. As an example in Bash,

export PYTHONPATH="$(pwd):${PYTHONPATH}"

Experiments

All experiment scripts utilize Fire and the arguments can directly be converted to CLI arguments. Appropriate functions are mentioned to look for CLI arguments to change. The default arguments are enough to reproduce results in the paper.

Toy Dataset

CLI Arguments: See toy method.

python experiments/vargp.py toy

Split MNIST

CLI Arguments: See split_mnist method.

python experiments/vargp.py s-mnist

Permuted MNIST

CLI Arguments: See permuted_mnist method.

python experiments/vargp.py p-mnist

Checkpoints and Graphs

The checkpoints files can be downloaded here. Extract contents of the zip file into notebooks/results.

All graphs in the paper can now be generated via code in the notebooks.

Acknowledgements

SK was supported by the Uber AI Residency program.

License

Apache 2.0

About

Variational Auto-Regressive Gaussian Processes for Continual Learning

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 71.1%
  • Jupyter Notebook 28.9%