Overfitting In Contrastive Learning?
Zachary Rabin, Jim Davis, Benjamin Lewis, Matthew Scherreik
7/16/2024
cs.LG
No confident code implementation found for this paper. 2 possible matches can be shown below.
Abstract
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.
