Label-Imbalanced and Group-Sensitive Classification under Overparameterization

Aug-16-2025, 10:23:27 GMT–Neural Information Processing Systems

Classical methods, such as weighted cross-entropy, fail when training deep nets to the terminal phase of training (TPT), that is training beyond zero training error.

adjustment, artificial intelligence, machine learning, (16 more...)

Neural Information Processing Systems

Aug-16-2025, 10:23:27 GMT

Conferences PDF

Add feedback

Country:
- North America > United States > California (0.28)

Genre:
- Research Report > New Finding (0.68)

Technology:
- Information Technology > Artificial Intelligence
  - Vision (1.00)
  - Machine Learning > Statistical Learning (1.00)

Duplicate Docs Excel Report

Title
Label-Imbalanced and Group-Sensitive Classification under Overparameterization

Similar Docs Excel Report more

Title	Similarity	Source
None found