Learning embeddings into entropic Wasserstein spaces
© 7th International Conference on Learning Representations, ICLR 2019. All Rights Reserved. Euclidean embeddings of data are fundamentally limited in their ability to capture latent semantic structures, which need not conform to Euclidean spatial assumptions. Here we consider an alternative, which e...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
2021-11-08T17:43:35Z.
|
| Subjects: | |
| Online Access: | Get fulltext |