Learning noisy linear classifiers via adaptive and selective sampling

DOI10.1007/S10994-010-5191-XzbMATH Open1237.68139OpenAlexW2132162087WikidataQ59538566 ScholiaQ59538566MaRDI QIDQ413852FDOQ413852

Authors: Giovanni Cavallanti, Nicolò Cesa-Bianchi, Claudio Gentile 

Publication date: 8 May 2012

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10994-010-5191-x

Recommendations

• scientific article; zbMATH DE number 5957363
• Learning probabilistic linear-threshold classifiers via selective sampling.
• Rates of convergence in active learning
• Active learning via perfect selective classification
• Selective sampling and active learning from single and multiple teachers

zbMATH Keywords

adaptive samplingactive learninglinear classificationselective samplinglow noise

Mathematics Subject Classification ID

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

Cites Work

• Prediction, Learning, and Games
• Convexity, Classification, and Risk Bounds
• Optimal aggregation of classifiers in statistical learning.
• Theory of Classification: a Survey of Some Recent Advances
• Fast rates for support vector machines using Gaussian kernels
• Selective sampling using the query by committee algorithm
• Agnostic active learning
• Title not available (Why is that?)
• A Second-Order Perceptron Algorithm
• Margin Based Active Learning
• Accurate error bounds for the eigenvalues of the kernel matrix
• On the Eigenspectrum of the Gram Matrix and the Generalization Error of Kernel-PCA
• Incremental algorithms for hierarchical classification
• Competitive On-line Statistics
• Relative loss bounds for on-line density estimation with the exponential family of distributions
• Active learning with multiple views
• Queries revisited.
• Apple tasting.
• Statistical properties of kernel principal component analysis
• Rates of convergence in active learning
• Active Learning in the Non-realizable Case
• Online Regularized Classification Algorithms
• Minimax Bounds for Active Learning
• A new technique of non‐linear statistic prediction and its application in atmospheric systems
• Learning Theory

Cited In (7)

• On the foundations of noise-free selective classification
• Active learning for cost-sensitive classification
• Title not available (Why is that?)
• Surrogate losses in passive and active learning
• Learning probabilistic linear-threshold classifiers via selective sampling.
• Statistical active learning algorithms for noise tolerance and differential privacy
• Integrated Fisher linear discriminants: an empirical study

This page was built for publication: Learning noisy linear classifiers via adaptive and selective sampling

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q413852)