← Back to papers
2014 AISTATS AISTATS 2014

PAC-Bayesian Theory for Transductive Learning

Abstract

We propose a PAC-Bayesian analysis of the transductive learning setting, introduced by Vapnik [2008], by proposing a family of new bounds on the generalization error. Some of them are derived from their counterpart in the inductive setting, and others are new. We also compare their behavior.

🌉 Interdisciplinary Bridge — Artificial Intelligence and Machine Learning
🐣 Hot Topic Early Bird — learning theory
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio

Authors

Luc Bégin , Pascal Germain , François Laviolette , Jean-Francis Roy

Topics

Artificial Intelligence > Learning Paradigms > Transfer Learning Machine Learning > Learning Types > Semi-Supervised Learning Machine Learning > Optimization & Theory > Bayesian Inference Machine Learning > Optimization & Theory > Learning Theory Machine Learning > Optimization & Theory > Statistical Learning

Keywords

learning theory transductive learning generalization error generalization bound pac-bayesian theory
Download PDF

Related papers

Improved Bounds for Online Learning Over the Permutahedron and Other Ranking Polytopes 2014
Sparse Bayesian Variable Selection for the Identification of Antigenic Variability in the Foot-and-Mouth Disease Virus 2014
Analytic Long-Term Forecasting with Periodic Gaussian Processes 2014
Exploiting the Limits of Structure Learning via Inherent Symmetry 2014
Collaborative Ranking for Local Preferences 2014