"Gradient Descent with Identity Initialization Efficiently Learns ..."

Peter L. Bartlett, David P. Helmbold, Philip M. Long (2019)

> Home

Details and statistics

DOI: 10.1162/NECO_A_01164

access: closed

type: Journal Article

metadata version: 2020-09-01

- view
  - electronic edition via DOI
  - unpaywalled version
  authority control:
- export record
  dblp key:
  - journals/neco/BartlettHL19
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/journals/neco/BartlettHL19
Peter L. Bartlett, David P. Helmbold, Philip M. Long:
Gradient Descent with Identity Initialization Efficiently Learns Positive-Definite Linear Transformations by Deep Residual Networks. Neural Comput. 31(3) (2019)

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.