Information-Theoretic Equivalence of Entropic Multi-Marginal Optimal Transport: A Theory for Multi-Agent Communication
Fuente:
arXiv
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2022
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914690300379136 |
|---|---|
| author | Wang, Shuchan |
| author_facet | Wang, Shuchan |
| contents | In this paper, we propose our information-theoretic equivalence of entropic multi-marginal optimal transport (MOT). This equivalence can be easily reduced to the case of entropic optimal transport (OT). Because OT is widely used to compare differences between knowledge or beliefs, we apply this result to the communication between agents with different beliefs. Our results formally prove the statement that entropic OT is information-theoretically optimal given by Wang et al. [2020] and generalize it to the multi-agent case. We believe that our work can shed light on OT theory in future multi-agent teaming systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2208_10256 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Information-Theoretic Equivalence of Entropic Multi-Marginal Optimal Transport: A Theory for Multi-Agent Communication Wang, Shuchan Information Theory Artificial Intelligence Robotics In this paper, we propose our information-theoretic equivalence of entropic multi-marginal optimal transport (MOT). This equivalence can be easily reduced to the case of entropic optimal transport (OT). Because OT is widely used to compare differences between knowledge or beliefs, we apply this result to the communication between agents with different beliefs. Our results formally prove the statement that entropic OT is information-theoretically optimal given by Wang et al. [2020] and generalize it to the multi-agent case. We believe that our work can shed light on OT theory in future multi-agent teaming systems. |
| title | Information-Theoretic Equivalence of Entropic Multi-Marginal Optimal Transport: A Theory for Multi-Agent Communication |
| topic | Information Theory Artificial Intelligence Robotics |
| url | https://arxiv.org/abs/2208.10256 |