paper-with-me

홈 › Papers

Contrastive Learning with Nasty Noise

2025-02-25 · Ziruo Zhao

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.

📄 PDF Abstract BibTeX arXiv:2502.17872

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningPAC learningRepresentation Learning

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Is nasty noise actually harder than malicious noise?

2025-11-12 · Guy Blanc, Yizhi Huang, Tal Malkin, Rocco A. Servedio arxiv

We consider the relative abilities and limitations of computationally efficient algorithms for learning in the presence of noise, under two well-studied and challenging adversarial noise models for learning Boolean funct…

Robust Learning with Optimal Error

2026-04-02 · Guy Blanc arxiv

We construct algorithms with optimal error for learning with adversarial noise. The overarching theme of this work is that the use of \textsl{randomized} hypotheses can substantially improve upon the best error rates ach…

Learning Geometric Concepts with Nasty Noise

2017-07-05 · Ilias Diakonikolas, Daniel M. Kane, Alistair Stewart

We study the efficient learnability of geometric concept classes - specifically, low-degree polynomial threshold functions (PTFs) and intersections of halfspaces - when a fraction of the data is adversarially corrupted. …

LEMMAOutlier DetectionPAC learning

PAC learning with nasty noise

2002-10-16 · Theoretical Computer Science 2002 10 · Nader H Bshouty, Nadav Eiron, Eyal Kushilevitz

We introduce a new model for learning in the presence of noise, which we call the Nasty Noise model. This model generalizes previously considered models of learning with noise. The learning process in this model, which i…

PAC learning

Distilling the Undistillable: Learning from a Nasty Teacher

2022-10-21 · Surgan Jandial, Yash Khasbage, Arghya Pal, Vineeth N Balasubramanian 외

The inadvertent stealing of private/sensitive information using Knowledge Distillation (KD) has been getting significant attention recently and has guided subsequent defense efforts considering its critical nature. Recen…

Knowledge Distillation