Skip to content

Commit

Permalink
Initial Commit
Browse files Browse the repository at this point in the history
  • Loading branch information
ericzhao28 committed Oct 14, 2022
0 parents commit cfe84ad
Show file tree
Hide file tree
Showing 25 changed files with 3,447 additions and 0 deletions.
Binary file added .DS_Store
Binary file not shown.
12 changes: 12 additions & 0 deletions .gitignore
Original file line number Diff line number Diff line change
@@ -0,0 +1,12 @@
*.swp
*.swo
*.pyc
**/*.pyc
**/*.swp
**/*.swo
logs
slurm_logs
multiNLI
waterbirds
celebA
slurm/execute_*
13 changes: 13 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,13 @@
# On-Demand Sampling: Learning Optimally from Multiple Distributions

This is an early-release of the code used in the experiments of the Neurips 2022 paper [On-Demand Sampling:
Learning Optimally from Multiple Distributions (HJZ 22)](https://eric-zhao.com/files/On-Demand%20Sampling%20%5bNeurips%202022%5d.pdf).

### Instructions
First, download the Waterbirds, MultiNLI, and CelebA datasets to the root of this project.
Then, run `ready.sh`, which will call `run.sh`.
The latter script will run the experiments.
When complete, the paper's figures can be reproduced by running the `generate_paper_results.py` script.

### Acknowledgements
This codebase is based in large part on the codebase of [the Group DRO implementation of the original authors of S. Sagawa, et al. 2019](https://github.com/kohpangwei/group_DRO).
Loading

0 comments on commit cfe84ad

Please sign in to comment.