paper-with-me

Papers

Multi-View Majority Vote Learning Algorithms: Direct Minimization of PAC-Bayesian Bounds

2024-11-09 · Mehdi Hennequin, Abdelkrim Zitouni, Khalid Benabdeslem, Haytham Elghazel, Yacine GACI

The PAC-Bayesian framework has significantly advanced the understanding of statistical learning, particularly for majority voting methods. Despite its successes, its application to multi-view learning -- a setting with multiple complementary data representations -- remains underexplored. In this work, we extend PAC-Bayesian theory to multi-view learning, introducing novel generalization bounds based on R\'enyi divergence. These bounds provide an alternative to traditional Kullback-Leibler divergence-based counterparts, leveraging the flexibility of R\'enyi divergence. Furthermore, we propose first- and second-order oracle PAC-Bayesian bounds and extend the C-bound to multi-view settings. To bridge theory and practice, we design efficient self-bounding optimization algorithms that align with our theoretical results.

📄 PDF Abstract BibTeX arXiv:2411.06276

Code (0)

등록된 구현이 없습니다.

Tasks

Generalization BoundsMULTI-VIEW LEARNING

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Multiview Learning of Weighted Majority Vote by Bregman Divergence Minimization

2018-05-25 · Anil Goyal, Emilie Morvant, Massih-Reza Amini

We tackle the issue of classifier combinations when observations have multiple views. Our method jointly learns view-specific weighted majority vote classifiers (i.e. for each view) over a set of base voters, and a secon…

Document ClassificationMultilingual text classificationMultiview LearningText Classification

Self-Bounding Majority Vote Learning Algorithms by the Direct Minimization of a Tight PAC-Bayesian C-Bound

2021-04-28 · Paul Viallard, Pascal Germain, Amaury Habrard, Emilie Morvant

In the PAC-Bayesian literature, the C-Bound refers to an insightful relation between the risk of a majority vote classifier (under the zero-one loss) and the first two moments of its margin (i.e., the expected margin and…

DiversityGeneralization Bounds

On the disintegration of the stochastic majority vote: From PAC-Bayesian bounds to a self-bounding algorithm

2026-09-15 · Julien Bastian, Benjamin Leblanc, Pascal Germain, Amaury Habrard 외 arxiv

Weighted majority votes are central to many successful ensemble methods. PAC-Bayesian theory provides tight generalization guarantees for such models by analyzing the expected risk of stochastic classifiers, while analyz…

New Bounds on the Accuracy of Majority Voting for Multi-Class Classification

2023-09-18 · Sina Aeeneh, Nikola Zlatanov, Jiangshan Yu

Majority voting is a simple mathematical function that returns the value that appears most often in a set. As a popular decision fusion technique, the majority voting function (MVF) finds applications in resolving confli…

Ensemble LearningMulti-class Classification

On the Byzantine Fault Tolerance of signSGD with Majority Vote

2025-02-26 · Emanuele Mengoli, Luzius Moll, Virgilio Strozzi, El-Mahdi El-Mhamdi

In distributed learning, sign-based compression algorithms such as signSGD with majority vote provide a lightweight alternative to SGD with an additional advantage: fault tolerance (almost) for free. However, for signSGD…