Unlabeled data does provably help

DOI10.4230/LIPICS.STACS.2013.185zbMATH Open1354.68221OpenAlexW1985520241MaRDI QIDQ2957883FDOQ2957883

Authors: Malte Darnstädt, Hans Ulrich Simon, Balázs Szörényi 

Publication date: 30 January 2017

Full work available at URL: https://dblp.uni-trier.de/db/conf/stacs/stacs2013.html#DarnstadtSS13

Recommendations

• A discriminative model for semi-supervised learning
• Open Problems in Efficient Semi-supervised PAC Learning
• Learning Theory
• On semi-supervised learning
• Learning Privately with Labeled and Unlabeled Examples

zbMATH Keywords

semi-supervised learningalgorithmic learningsample complexity

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cited In (6)

• Semi-supervised interpolation in an anticausal learning scenario
• Learning Theory
• Open Problems in Efficient Semi-supervised PAC Learning
• A discriminative model for semi-supervised learning
• On the complexity of learning a class ratio from unlabeled data
• Learning a classifier when the labeling is known

This page was built for publication: Unlabeled data does provably help

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2957883)