Semi-flat minima and saddle points by embedding neural networks to overparameterization

Kenji Fukumizu, Shoichiro Yamaguchi, Yoh-ichi Mototake, Mirai Tanaka

Feb-13-2026, 09:20:32 GMT–Neural Information Processing Systems

We theoretically study the landscape of the training error for neural networks in overparameterized cases.

artificial intelligence, machine learning, training error, (16 more...)

Neural Information Processing Systems

Feb-13-2026, 09:20:32 GMT

Conferences PDF

Country:
- Asia > Japan
  - Honshū > Kantō > Tokyo Metropolis Prefecture > Tokyo (0.05)
- North America
  - Canada > British Columbia
    - Metro Vancouver Regional District > Vancouver (0.04)
  - United States (0.04)

Technology:
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks (0.67)

Duplicate Docs Excel Report

Title
Semi-flat minima and saddle points by embedding neural networks to overparameterization

Similar Docs Excel Report more

Title	Similarity	Source
None found