A Characterization of Multioutput Learnability
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915031757619200 |
|---|---|
| author | Raman, Vinod Subedi, Unique Tewari, Ambuj |
| author_facet | Raman, Vinod Subedi, Unique Tewari, Ambuj |
| contents | We consider the problem of learning multioutput function classes in the batch and online settings. In both settings, we show that a multioutput function class is learnable if and only if each single-output restriction of the function class is learnable. This provides a complete characterization of the learnability of multilabel classification and multioutput regression in both batch and online settings. As an extension, we also consider multilabel learnability in the bandit feedback setting and show a similar characterization as in the full-feedback setting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2301_02729 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | A Characterization of Multioutput Learnability Raman, Vinod Subedi, Unique Tewari, Ambuj Machine Learning We consider the problem of learning multioutput function classes in the batch and online settings. In both settings, we show that a multioutput function class is learnable if and only if each single-output restriction of the function class is learnable. This provides a complete characterization of the learnability of multilabel classification and multioutput regression in both batch and online settings. As an extension, we also consider multilabel learnability in the bandit feedback setting and show a similar characterization as in the full-feedback setting. |
| title | A Characterization of Multioutput Learnability |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2301.02729 |