# Contrastive Learning with Nasty Noise

arXiv: https://arxiv.org/abs/2502.17872 · HTML: https://mlsanity.com/paper/2502.17872/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 5 references that are in the map.
- First posted on arXiv 25 Feb 2025.

## Builds on (most cited first, 3 of 3)

- [A Theoretical Analysis of Contrastive Unsupervised Representation Learning](https://mlsanity.com/paper/1902.09229/) (2019)
- [Generalization Analysis for Contrastive Representation Learning](https://mlsanity.com/paper/2302.12383/) (2023)
- [Optimal Sample Complexity of Contrastive Learning](https://mlsanity.com/paper/2312.00379/) (2023)

## Abstract (arXiv)

Contrastive learning has emerged as a powerful paradigm for self-supervised representation learning. This work analyzes the theoretical limits of contrastive learning under nasty noise, where an adversary modifies or replaces training samples. Using PAC learning and VC-dimension analysis, lower and upper bounds on sample complexity in adversarial settings are established. Additionally, data-dependent sample complexity bounds based on the l2-distance function are derived.