Datasets for Studying Generalization from Easy to Hard Examples
Avi Schwarzschild, Eitan Borgnia, Arjun Gupta, Arpit Bansal, Zeyad Emam, Furong Huang, Micah Goldblum, Tom Goldstein
arXiv:2108.06011v215 citations
AI Analysis
This work addresses a fundamental problem in machine learning for researchers, but it appears incremental as it focuses on dataset creation without novel methodological advances.
The authors introduced new datasets to investigate how models generalize from easy to hard examples, but no specific results or numbers were provided.
We describe new datasets for studying generalization from easy to hard examples.