-
Notifications
You must be signed in to change notification settings - Fork 1
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
0 parents
commit cfe84ad
Showing
25 changed files
with
3,447 additions
and
0 deletions.
There are no files selected for viewing
Binary file not shown.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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_* |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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). |
Oops, something went wrong.