Low Dimensional Trajectory Hypothesis is True : DNNs Can Be Trained in Tiny Subspaces
Deep neural networks (DNNs) usually contain massive parameters, but there is redundancy such that it is guessed that they could be trained in low-dimensional subspaces. In this paper, we propose a Dynamic Linear Dimensionality Reduction (DLDR) based on the low-dimensional properties of the training...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 45(2023), 3 vom: 26. März, Seite 3411-3420
|
|---|
| 1. Verfasser: |
Li, Tao
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Tan, Lei,
Huang, Zhehao,
Tao, Qinghua,
Liu, Yipeng,
Huang, Xiaolin |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2023
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article |
|---|