<ul><li>ADA (Anchor Data Augmentation) outperforms ERM (Expected Risk Minimization) and competes with C-Mixup in in-distribution generalization tasks.</li><li>ADA is evaluated and compared to other approaches on tasks involving in-distribution generalization using various datasets.</li><li>ADA consistently improves regression fit compared to ERM and is superior to other data augmentation strategies.</li><li>ADA shows significant improvement in reducing error for the Airfoil dataset.</li></ul>

ADA Outperforms ERM and Competes with C-Mixup in In-Distribution Generalization Tasks

Discover more