Learning noisy linear classifiers via adaptive and selective sampling

DOI10.1007/s10994-010-5191-xzbMath1237.68139OpenAlexW2132162087WikidataQ59538566 ScholiaQ59538566MaRDI QIDQ413852

Claudio Gentile, Nicolò Cesa-Bianchi, Giovanni Cavallanti

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

zbMATH Keywords

active learningadaptive samplinglinear classificationselective samplinglow noise

Mathematics Subject Classification ID

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

Related Items

Integrated Fisher linear discriminants: an empirical study, Surrogate losses in passive and active learning, Unnamed Item, Statistical active learning algorithms for noise tolerance and differential privacy

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Fast rates for support vector machines using Gaussian kernels
• Selective sampling using the query by committee algorithm
• Queries revisited.
• Apple tasting.
• Optimal aggregation of classifiers in statistical learning.
• Statistical properties of kernel principal component analysis
• Rates of convergence in active learning
• Agnostic active learning
• Theory of Classification: a Survey of Some Recent Advances
• Active Learning in the Non-realizable Case
• On the Eigenspectrum of the Gram Matrix and the Generalization Error of Kernel-PCA
• Online Regularized Classification Algorithms
• Minimax Bounds for Active Learning
• A new technique of non‐linear statistic prediction and its application in atmospheric systems
• Competitive On-line Statistics
• A Second-Order Perceptron Algorithm
• Margin Based Active Learning
• Prediction, Learning, and Games
• Learning Theory
• Convexity, Classification, and Risk Bounds
• Relative loss bounds for on-line density estimation with the exponential family of distributions