torchrec
torchrec copied to clipboard
Add Regression AUC (RAUC) metrics
Summary: Implement regression AUC metrics. Regression AUC is an extension of classification AUC. See Section 4.1.1 in https://arxiv.org/ftp/arxiv/papers/1205/1205.2618.pdf for related discussions.
On a high level, regression AUC is an extension of the traditional AUC for classification through the probabilistic interpretation: the area under the curve is equal to the probability that a classifier will rank a randomly chosen positive instance higher than a randomly chosen negative one.
We utilize merge sort to optimize time complexity to O(nlog(n)).
#TODO:
- need more test cases.
- grouped_rauc is not verified.
f535371503
{F1461111882}
Reviewed By: zainhuda
Differential Revision: D53377225
This pull request was exported from Phabricator. Differential Revision: D53377225
This pull request was exported from Phabricator. Differential Revision: D53377225
This pull request was exported from Phabricator. Differential Revision: D53377225
This pull request was exported from Phabricator. Differential Revision: D53377225
This pull request was exported from Phabricator. Differential Revision: D53377225
This pull request was exported from Phabricator. Differential Revision: D53377225