Overfitting In Contrastive Learning?
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_ | 1866916365111132160 |
|---|---|
| author | Rabin, Zachary Davis, Jim Lewis, Benjamin Scherreik, Matthew |
| author_facet | Rabin, Zachary Davis, Jim Lewis, Benjamin Scherreik, Matthew |
| contents | Overfitting describes a machine learning phenomenon where the model fits too closely to the training data, resulting in poor generalization. While this occurrence is thoroughly documented for many forms of supervised learning, it is not well examined in the context of unsupervised learning. In this work we examine the nature of overfitting in unsupervised contrastive learning. We show that overfitting can indeed occur and the mechanism behind overfitting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_15863 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Overfitting In Contrastive Learning? Rabin, Zachary Davis, Jim Lewis, Benjamin Scherreik, Matthew Machine Learning Overfitting describes a machine learning phenomenon where the model fits too closely to the training data, resulting in poor generalization. While this occurrence is thoroughly documented for many forms of supervised learning, it is not well examined in the context of unsupervised learning. In this work we examine the nature of overfitting in unsupervised contrastive learning. We show that overfitting can indeed occur and the mechanism behind overfitting. |
| title | Overfitting In Contrastive Learning? |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2407.15863 |