A discriminative model for semi-supervised learning

DOI10.1145/1706591.1706599MaRDI QIDQ3578199zbMATH OpenOpenAlexFDO

Authors Maria-Florina Balcan, Avrim Blum

Publication date 14 July 2010

Published in Journal of the ACM (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1145/1706591.1706599

zbMATH Keywords

co-trainingcover boundsdata dependent SRMefficient learning algorithmsmachine learningmulti-view classificationsample complexitysemi-supervised learningstructural risk minimization (SRM)uniform convergence boundsvalue of unlabeled data

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Learning Theory
• Open Problems in Efficient Semi-supervised PAC Learning
• Unlabeled data does provably help
• Supervised learning and co-training
• Supervised learning and co-training

Cited in

(39)

• Probability-one homotopy methods for constrained clustering
• Maximum margin semi-supervised learning with irrelevant data
• Simple strategies for semi-supervised feature selection
• Semi-supervised classification via simultaneous label and discriminant embedding estimation
• Discriminative clustering with representation learning with any ratio of labeled to unlabeled data
• Discriminative deep belief networks for visual data classification
• Discriminative semi-supervised learning of dynamical systems for motion estimation
• Smart PAC-learners
• On semi-supervised learning
• Unsupervised supervised learning. I: Estimating classification and regression errors without labels
• PAC-Bayesian analysis of co-clustering and beyond
• Improved generative semisupervised learning based on finely grained component-conditional class labeling
• Unlabeled data does provably help
• Supervised learning and co-training
• Learning a classifier when the labeling is known
• Data augmentation via Lévy processes
• Introduction to semi-supervised learning.
• Supervised learning and co-training
• A theory of learning with corrupted labels
• scientific article; zbMATH DE number 1931857 (Why is no real title available?)
• scientific article; zbMATH DE number 1832358 (Why is no real title available?)
• scientific article; zbMATH DE number 1843022 (Why is no real title available?)
• End-user feature labeling: supervised and semi-supervised approaches based on locally-weighted logistic regression
• Semi-Supervised Approaches to Efficient Evaluation of Model Prediction Performance
• Self-paced multi-view co-training
• Semi-supervised learning in causal and anticausal settings
• Semisupervised Learning for Computational Linguistics
• Making use of unlabeled data in semi-supervised learning
• Unsupervised supervised learning. II: Margin-based classification without labels
• Open Problems in Efficient Semi-supervised PAC Learning
• Learning Theory
• scientific article; zbMATH DE number 2243385 (Why is no real title available?)
• Learning using privileged information: similarity control and knowledge transfer
• Semi-supervised learning using differentiable reasoning
• PAC-learning with approximate predictors
• Lifting uniform learners via distributional decomposition
• Realizable learning is all you need
• Learning from fuzzy labels: theoretical issues and algorithmic solutions
• Stochastic feature mapping for PAC-Bayes classification

This page was built for publication: A discriminative model for semi-supervised learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3578199)