Saved in:
Bibliographic Details
Main Author: Zhao, Ziruo
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.17872
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • 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.