paper-with-me

홈 › Papers

Localized Complexities for Transductive Learning

2014-11-26 · Ilya Tolstikhin, Gilles Blanchard, Marius Kloft

We show two novel concentration inequalities for suprema of empirical processes when sampling without replacement, which both take the variance of the functions into account. While these inequalities may potentially have broad applications in learning theory in general, we exemplify their significance by studying the transductive setting of learning theory. For which we provide the first excess risk bounds based on the localized complexity of the hypothesis class, which can yield fast rates of convergence also in the transductive learning setting. We give a preliminary analysis of the localized complexities for the prominent case of kernel classes.

📄 PDF Abstract BibTeX arXiv:1411.7200

Code (0)

등록된 구현이 없습니다.

Tasks

Learning TheoryTransductive Learning

Similar Papers 제목 키워드 기반

Transductive Learning Is Compact

2024-02-15 · Julian Asilis, Siddartha Devic, Shaddin Dughmi, Vatsal Sharan 외

We demonstrate a compactness result holding broadly across supervised learning with a general class of loss functions: Any hypothesis class $H$ is learnable with transductive sample complexity $m$ precisely when all of i…

Learning TheoryPAC learningTransductive Learning

Optimal Mistake Bounds for Transductive Online Learning

2025-12-14 · Zachary Chase, Steve Hanneke, Shay Moran, Jonathan Shafer arxiv

We resolve a 30-year-old open problem concerning the power of unlabeled data in online learning by tightly quantifying the gap between transductive and standard online learning. In the standard setting, the optimal mista…

Sharp Generalization of Transductive Learning: A Transductive Local Rademacher Complexity Approach

2023-09-28 · Yingzhen Yang

We introduce a new tool, Transductive Local Complexity (TLC), designed to analyze the generalization performance of transductive learning methods and inspire the development of new algorithms in this domain. Our work ext…

Generalization BoundsLearning TheoryTransductive Learning

Is Transductive Learning Equivalent to PAC Learning?

2024-05-08 · Shaddin Dughmi, Yusuf Kalayci, Grayson York

Much of learning theory is concerned with the design and analysis of probably approximately correct (PAC) learners. The closely related transductive model of learning has recently seen more scrutiny, with its learners of…

Binary ClassificationLearning TheoryPAC learningTransductive Learning

Early stopping for kernel boosting algorithms: A general analysis with localized complexities

2017-07-05 · NeurIPS 2017 12 · Yuting Wei, Fanny Yang, Martin J. Wainwright

Early stopping of iterative algorithms is a widely-used form of regularization in statistics, commonly used in conjunction with boosting and related gradient-type algorithms. Although consistency results have been establ…