paper-with-me

Papers

Generalization Analysis for Contrastive Representation Learning

2023-02-24 · Yunwen Lei, Tianbao Yang, Yiming Ying, Ding-Xuan Zhou

Recently, contrastive learning has found impressive success in advancing the state of the art in solving various machine learning tasks. However, the existing generalization analysis is very limited or even not meaningful. In particular, the existing generalization error bounds depend linearly on the number $k$ of negative examples while it was widely shown in practice that choosing a large $k$ is necessary to guarantee good generalization of contrastive learning in downstream tasks. In this paper, we establish novel generalization bounds for contrastive learning which do not depend on $k$, up to logarithmic terms. Our analysis uses structural results on empirical covering numbers and Rademacher complexities to exploit the Lipschitz continuity of loss functions. For self-bounding Lipschitz loss functions, we further improve our results by developing optimistic bounds which imply fast rates in a low noise condition. We apply our results to learning with both linear representation and nonlinear representation by deep neural networks, for both of which we derive Rademacher complexity bounds to get improved generalization bounds.

📄 PDF Abstract BibTeX arXiv:2302.12383

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningGeneralization BoundsRepresentation Learning

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Using contrastive learning to improve the performance of steganalysis schemes

2021-03-01 · Yanzhen Ren, YiWen Liu, Lina Wang

To improve the detection accuracy and generalization of steganalysis, this paper proposes the Steganalysis Contrastive Framework (SCF) based on contrastive learning. The SCF improves the feature representation of stegana…

Contrastive LearningSteganalysis

Generalization Analysis for Contrastive Representation Learning under Non-IID Settings

2025-05-08 · Nong Minh Hieu, Antoine Ledent

Contrastive Representation Learning (CRL) has achieved impressive success in various domains in recent years. Nevertheless, the theoretical understanding of the generalization behavior of CRL is limited. Moreover, to the…

Contrastive LearningGeneralization BoundsRepresentation Learning

Towards Understanding the Mechanism of Contrastive Learning via Similarity Structure: A Theoretical Analysis

2023-04-01 · Hiroki Waida, Yuichiro Wada, Léo Andéol, Takumi Nakagawa 외

Contrastive learning is an efficient approach to self-supervised representation learning. Although recent studies have made progress in the theoretical understanding of contrastive learning, the investigation of how to c…

Contrastive LearningRepresentation Learning

Revisiting Theory of Contrastive Learning for Domain Generalization

2025-12-02 · Ali Alvandi, Mina Rezaei arxiv

Contrastive learning is among the most popular and powerful approaches for self-supervised representation learning, where the goal is to map semantically similar samples close together while separating dissimilar ones in…

Representation LearningDomain GeneralizationContrastive Learning

Generalization Beyond Feature Alignment: Concept Activation-Guided Contrastive Learning

2022-11-13 · Yibing Liu, Chris Xing Tian, Haoliang Li, Shiqi Wang

Learning invariant representations via contrastive learning has seen state-of-the-art performance in domain generalization (DG). Despite such success, in this paper, we find that its core learning strategy -- feature ali…

Contrastive LearningDiversityDomain Generalization