Contrastive Learning, Multi-View Redundancy, and Linear Models
Abstract
Self-supervised learning is an empirically successful approach to unsupervised learning based on creating artificial supervised learning problems. A popular self-supervised approach to representation learning is contrastive learning, which leverages naturally occurring pairs of similar and dissimilar data points, or multiple views of the same data. This work provides a theoretical analysis of contrastive learning in the multi-view setting, where two views of each datum are available. The main result is that linear functions of the learned representations are nearly optimal on downstream prediction tasks whenever the two views provide redundant information about the label.
Cite
Text
Tosh et al. "Contrastive Learning, Multi-View Redundancy, and Linear Models." Proceedings of the 32nd International Conference on Algorithmic Learning Theory, 2021.Markdown
[Tosh et al. "Contrastive Learning, Multi-View Redundancy, and Linear Models." Proceedings of the 32nd International Conference on Algorithmic Learning Theory, 2021.](https://mlanthology.org/alt/2021/tosh2021alt-contrastive/)BibTeX
@inproceedings{tosh2021alt-contrastive,
title = {{Contrastive Learning, Multi-View Redundancy, and Linear Models}},
author = {Tosh, Christopher and Krishnamurthy, Akshay and Hsu, Daniel},
booktitle = {Proceedings of the 32nd International Conference on Algorithmic Learning Theory},
year = {2021},
pages = {1179-1206},
volume = {132},
url = {https://mlanthology.org/alt/2021/tosh2021alt-contrastive/}
}