Average Top-k Aggregate Loss for Supervised Learning
In this work, we introduce the average top- k ( ATk) loss, which is the average over the k largest individual losses over a training data, as a new aggregate loss for supervised learning. We show that the ATk loss is a natural generalization of the two widely used aggregate losses, namely the averag...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 44(2022), 1 vom: 30. Jan., Seite 76-86
|
|---|
| 1. Verfasser: |
Lyu, Siwei
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Fan, Yanbo,
Ying, Yiming,
Hu, Bao-Gang |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2022
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article
Research Support, Non-U.S. Gov't
Research Support, U.S. Gov't, Non-P.H.S. |
|---|