Multi-View Majority Vote Learning Algorithms: Direct Minimization of PAC-Bayesian Bounds
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 28 of its 74 references that are in the map. First posted on arXiv 9 Nov 2024.
Builds on
28 of 74 references.
References · 28
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
- 2017Decoupled Weight Decay Regularizationcited by 1,722
- 2017Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Datacited by 527
- 2021User-friendly introduction to PAC-Bayes boundscited by 234
- 2017EMNIST: an extension of MNIST to handwritten letterscited by 212
- 2013A Survey on Multi-view Learningcited by 152
- 2020Tighter risk certificates for neural networkscited by 112
- 2016A Strongly Quasiconvex PAC-Bayesian Boundcited by 54
- 2015Risk Bounds for the Majority Vote: From a PAC-Bayesian Analysis to a Learning Algorithmcited by 50
- 2020Second Order PAC-Bayesian Bounds for the Weighted Majority Votecited by 34
- 2021PAC-Bayes, MAC-Bayes and Conditional Mutual Information: Fast rate bounds that handle general VC classescited by 31
16 more
- 2018Learning Gaussian Processes by Minimizing PAC-Bayesian Generalization Boundscited by 24
- 2021How Tight Can PAC-Bayes be in the Small Data Regime?cited by 24
- 2021A General Framework for the Practical Disintegration of PAC-Bayesian Boundscited by 21
- 2021Learning Stochastic Majority Votes by Minimizing a PAC-Bayes Generalization Boundcited by 16
- 2022On Rademacher Complexity-based Generalization Bounds for Deep Learningcited by 16
- 2023Statistical Guarantees for Variational Autoencoders using PAC-Bayesian Theorycited by 16
- 2021A PAC-Bayes Analysis of Adversarial Robustnesscited by 13
- 2021Chebyshev-Cantelli PAC-Bayes-Bennett Inequality for the Weighted Majority Votecited by 13
- 2013Multi-view Laplacian Support Vector Machinescited by 9
- 2021Self-Bounding Majority Vote Learning Algorithms by the Direct Minimization of a Tight PAC-Bayesian C-Boundcited by 8
- 2015PAC-Bayesian Theorems for Domain Adaptation with Specialization to Linear Classifierscited by 4
- 2016Topic Model Based Multi-Label Classification from the Crowdcited by 4
- 2016PAC-Bayesian Analysis for a two-step Hierarchical Multiview Learning Approachcited by 4
- 2018Multiview Boosting by Controlling the Diversity and the Accuracy of View-specific Voterscited by 4
- 2014PAC-Bayes Analysis of Multi-view Learningcited by 3
- 2017Training Deep Networks without Learning Rates Through Coin Bettingcited by 2
Built on by
Citing papers per year: 2025: 1.
1 paper.