"Feature learning as alignment: a structural property of gradient descent ..."

Daniel Beaglehole, Ioannis Mitliagkas, Atish Agarwala (2024)

> Home

Details and statistics

DOI: —

access: open

type: Journal Article

metadata version: 2025-06-17

- view
  - electronic edition @ openreview.net (open access)
- export record
  dblp key:
  - journals/tmlr/BeagleholeMA24
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/journals/tmlr/BeagleholeMA24
Daniel Beaglehole, Ioannis Mitliagkas, Atish Agarwala:
Feature learning as alignment: a structural property of gradient descent in non-linear neural networks. Trans. Mach. Learn. Res. 2024 (2024)

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.