paper-with-me

Papers

Local Rademacher Complexity Bounds based on Covering Numbers

2015-10-06 · Yunwen Lei, Lixin Ding, Yingzhou Bi

This paper provides a general result on controlling local Rademacher complexities, which captures in an elegant form to relate the complexities with constraint on the expected norm to the corresponding ones with constraint on the empirical norm. This result is convenient to apply in real applications and could yield refined local Rademacher complexity bounds for function classes satisfying general entropy conditions. We demonstrate the power of our complexity bounds by applying them to derive effective generalization error bounds.

📄 PDF Abstract BibTeX arXiv:1510.01463

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Sharper Generalization Bounds for Transformer

2026-03-23 · Yawen Li, Tao Hu, Zhouhui Lian, Wan Tian 외 arxiv

This paper studies generalization error bounds for Transformer models. Based on the offset Rademacher complexity, we derive sharper generalization bounds for different Transformer architectures, including single-layer si…

Adversarial Rademacher Complexity of Deep Neural Networks

2022-11-27 · Jiancong Xiao, Yanbo Fan, Ruoyu Sun, Zhi-Quan Luo

Deep neural networks are vulnerable to adversarial attacks. Ideally, a robust model shall perform well on both the perturbed training data and the unseen perturbed test data. It is found empirically that fitting perturbe…

ARC

Approximate Description Length, Covering Numbers, and VC Dimension

2022-09-26 · Amit Daniely, Gal Katzhendler

Recently, Daniely and Granot [arXiv:1910.05697] introduced a new notion of complexity called Approximate Description Length (ADL). They used it to derive novel generalization bounds for neural networks, that despite subs…

Generalization Bounds

A Gapped Scale-Sensitive Dimension and Lower Bounds for Offset Rademacher Complexity

2025-09-24 · Zeyu Jia, Yury Polyanskiy, Alexander Rakhlin arxiv

We study gapped scale-sensitive dimensions of a function class in both sequential and non-sequential settings. We demonstrate that covering numbers for any uniformly bounded class are controlled above by these gapped dim…

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 meaningfu…

Contrastive LearningGeneralization BoundsRepresentation Learning