Self-supervised contrastive learning performs non-linear system identification
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915316312834048 |
|---|---|
| author | Laiz, Rodrigo González Schmidt, Tobias Schneider, Steffen |
| author_facet | Laiz, Rodrigo González Schmidt, Tobias Schneider, Steffen |
| contents | Self-supervised learning (SSL) approaches have brought tremendous success across many tasks and domains. It has been argued that these successes can be attributed to a link between SSL and identifiable representation learning: Temporal structure and auxiliary variables ensure that latent representations are related to the true underlying generative factors of the data. Here, we deepen this connection and show that SSL can perform system identification in latent space. We propose dynamics contrastive learning, a framework to uncover linear, switching linear and non-linear dynamics under a non-linear observation model, give theoretical guarantees and validate them empirically. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_14673 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Self-supervised contrastive learning performs non-linear system identification Laiz, Rodrigo González Schmidt, Tobias Schneider, Steffen Machine Learning Self-supervised learning (SSL) approaches have brought tremendous success across many tasks and domains. It has been argued that these successes can be attributed to a link between SSL and identifiable representation learning: Temporal structure and auxiliary variables ensure that latent representations are related to the true underlying generative factors of the data. Here, we deepen this connection and show that SSL can perform system identification in latent space. We propose dynamics contrastive learning, a framework to uncover linear, switching linear and non-linear dynamics under a non-linear observation model, give theoretical guarantees and validate them empirically. |
| title | Self-supervised contrastive learning performs non-linear system identification |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2410.14673 |