Rademacher complexities and bounding the excess risk in active learning

zbMATH Open1242.62088MaRDI QIDQ2896152FDOQ2896152

Authors: Vladimir Koltchinskii 

Publication date: 13 July 2012

Published in: Journal of Machine Learning Research (JMLR) (Search for Journal in Brave)

Full work available at URL: http://www.jmlr.org/papers/v11/koltchinskii10a.html

Recommendations

• Probability bounds for active learning in the regression problem
• The true sample complexity of active learning
• Minimax Bounds for Active Learning
• Minimax Bounds for Active Learning
• Statistical asymptotic theory of active learning
• 10.1162/153244303321897690
• scientific article; zbMATH DE number 1804106

zbMATH Keywords

capacity functiondisagreement coefficient

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05) Sequential statistical methods (62L99)

Cited In (13)

• Minimax Bounds for Active Learning
• Local Rademacher complexity-based learning guarantees for multi-task learning
• Recent advances in scaling-down sampling methods in machine learning
• Surrogate losses in passive and active learning
• Adaptive sensing performance lower bounds for sparse signal detection and support estimation
• Spatially-adaptive sensing in nonparametric regression
• Rates of convergence in active learning
• Regularized sample average approximation for high-dimensional stochastic optimization under low-rankness
• The true sample complexity of active learning
• Statistical active learning algorithms for noise tolerance and differential privacy
• A theory of transfer learning with applications to active learning
• High-Dimensional Learning Under Approximate Sparsity with Applications to Nonsmooth Estimation and Regularized Neural Networks
• Probability bounds for active learning in the regression problem

This page was built for publication: Rademacher complexities and bounding the excess risk in active learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2896152)