Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent

Jaehoon Lee, Lechao Xiao, Samuel Schoenholz, Yasaman Bahri, Roman Novak, Jascha Sohl-Dickstein, Jeffrey Pennington

Feb-11-2026, 10:57:02 GMT–Neural Information Processing Systems

Neural Information Processing Systems http://nips.cc/

artificial intelligence, ininternational conferenceon learning representation, machine learning, (10 more...)

Neural Information Processing Systems

Feb-11-2026, 10:57:02 GMT

Conferences PDF

Country:
- North America
  - United States > New York (0.04)
  - Canada
    - Ontario > Toronto (0.04)
    - British Columbia > Metro Vancouver Regional District
      - Vancouver (0.04)

Technology:
- Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning > Gradient Descent (0.40)

Duplicate Docs Excel Report

Title
Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent

Similar Docs Excel Report more

Title	Similarity	Source
None found