Broadcast Channel Cooperative Gain: An Operational Interpretation of Partial Information Decomposition
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912233504636928 |
|---|---|
| author | Tian, Chao Shamai, Shlomo |
| author_facet | Tian, Chao Shamai, Shlomo |
| contents | Partial information decomposition has recently found applications in biological signal processing and machine learning. Despite its impacts, the decomposition was introduced through an informal and heuristic route, and its exact operational meaning is unclear. In this work, we fill this gap by connecting partial information decomposition to the capacity of the broadcast channel, which has been well-studied in the information theory literature. We show that the synergistic information in the decomposition can be rigorously interpreted as the cooperative gain, or a lower bound of this gain, on the corresponding broadcast channel. This interpretation can help practitioners to better explain and expand the applications of the partial information decomposition technique. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_10878 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Broadcast Channel Cooperative Gain: An Operational Interpretation of Partial Information Decomposition Tian, Chao Shamai, Shlomo Information Theory Artificial Intelligence Machine Learning Partial information decomposition has recently found applications in biological signal processing and machine learning. Despite its impacts, the decomposition was introduced through an informal and heuristic route, and its exact operational meaning is unclear. In this work, we fill this gap by connecting partial information decomposition to the capacity of the broadcast channel, which has been well-studied in the information theory literature. We show that the synergistic information in the decomposition can be rigorously interpreted as the cooperative gain, or a lower bound of this gain, on the corresponding broadcast channel. This interpretation can help practitioners to better explain and expand the applications of the partial information decomposition technique. |
| title | Broadcast Channel Cooperative Gain: An Operational Interpretation of Partial Information Decomposition |
| topic | Information Theory Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2502.10878 |