Rates of convergence in active learning

DOI10.1214/10-AOS843zbMath1274.62510arXiv1103.1790MaRDI QIDQ2429933

Steve Hanneke

Publication date: 5 April 2011

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1103.1790

zbMATH Keywords

classificationmodel selectionstatistical learning theoryactive learningoracle inequalitiesselective samplingsequential design

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Computational learning theory (68Q32) Learning and adaptive systems in artificial intelligence (68T05) Sequential statistical design (62L05) Nonparametric inference (62G99)

Related Items (8)

Troubleshooting image segmentation models with human-in-the-loop ⋮ Learning noisy linear classifiers via adaptive and selective sampling ⋮ A theory of transfer learning with applications to active learning ⋮ Spatially-adaptive sensing in nonparametric regression ⋮ Adaptive sensing performance lower bounds for sparse signal detection and support estimation ⋮ Active Nearest-Neighbor Learning in Metric Spaces ⋮ Surrogate losses in passive and active learning ⋮ Unnamed Item

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Probability inequalities for empirical processes and a law of the iterated logarithm
• Risk bounds for statistical learning
• Rates of growth and sample moduli for weighted empirical processes indexed by sets
• Sample moduli for set-indexed Gaussian processes
• Estimation of dependences based on empirical data. Transl. from the Russian by Samuel Kotz
• Toward efficient agnostic learning
• Smooth discrimination analysis
• Optimal aggregation of classifiers in statistical learning.
• Weak convergence and empirical processes. With applications to statistics
• Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
• Concentration inequalities and asymptotic results for ratio type empirical processes
• Agnostic active learning
• Learnability and the Vapnik-Chervonenkis dimension
• Active Learning in the Non-realizable Case
• Minimax Bounds for Active Learning
• Neural Network Learning
• Margin Based Active Learning
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities

This page was built for publication: Rates of convergence in active learning