ADA vs C-Mixup: Performance on California and Boston Housing Datasets | HackerNoon
Briefly

In our experiments with housing datasets, we observed a significant improvement in model performance using Anchor Data Augmentation (ADA) compared to traditional methods like C-Mixup.
By employing ADA, we demonstrated that not only can regression models achieve enhanced in-distribution generalization, but they also exhibit improved robustness against out-of-distribution samples.
Read at Hackernoon
[
|
]