323746f0ae2fbd8b6f500dc2d5c5f898-Paper-Conference.pdf

Feb-8-2026, 05:34:52 GMT–Neural Information Processing Systems

Hence, in this infinite-width limit, it suffices that the smallest eigenvalue of the NTK is bounded away from0for gradient descent to reach zero loss.

artificial intelligence, machine learning, neurips, (18 more...)

Neural Information Processing Systems

Feb-8-2026, 05:34:52 GMT

Conferences PDF

Add feedback

Country:
- Europe
  - Austria (0.04)
  - Switzerland (0.04)

Technology:
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks (1.00)

Duplicate Docs Excel Report

Title
Memorization and Optimization in Deep Neural Networks with Minimum Over-parameterization

Similar Docs Excel Report more

Title	Similarity	Source
None found