"Low Dimensional Trajectory Hypothesis is True: DNNs Can Be Trained in Tiny ..."

Tao Li et al. (2023)

> Home

Details and statistics

DOI: 10.1109/TPAMI.2022.3178101

access: closed

type: Journal Article

metadata version: 2023-09-20

- view
  - electronic edition via DOI
  - unpaywalled version
  authority control:
- export record
  dblp key:
  - journals/pami/LiTHTLH23
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/journals/pami/LiTHTLH23
Tao Li, Lei Tan, Zhehao Huang, Qinghua Tao, Yipeng Liu, Xiaolin Huang:
Low Dimensional Trajectory Hypothesis is True: DNNs Can Be Trained in Tiny Subspaces. IEEE Trans. Pattern Anal. Mach. Intell. 45(3): 3411-3420 (2023)

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.