Surrogate losses in passive and active learning

DOI10.1214/19-EJS1635zbMath1433.62158arXiv1207.3772OpenAlexW1807095418MaRDI QIDQ2008623

Liu Yang, Steve Hanneke

Publication date: 26 November 2019

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1207.3772

zbMATH Keywords

classificationstatistical learning theoryactive learningselective samplingsequential designsurrogate loss functions

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05) Sequential statistical design (62L05)

Related Items (2)

Unnamed Item ⋮ Unnamed Item

Uses Software

• AdaBoost.MH

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Learning noisy linear classifiers via adaptive and selective sampling
• Oracle inequalities in empirical risk minimization and sparse recovery problems. École d'Été de Probabilités de Saint-Flour XXXVIII-2008.
• Fast learning rates for plug-in classifiers
• Rates of growth and sample moduli for weighted empirical processes indexed by sets
• Universal Donsker classes and metric entropy
• Decision theoretic generalizations of the PAC model for neural net and other learning applications
• Central limit theorems for empirical measures
• Toward efficient agnostic learning
• A decision-theoretic generalization of on-line learning and an application to boosting
• Smooth discrimination analysis
• Statistical behavior and consistency of classification methods based on convex risk minimization.
• Optimal aggregation of classifiers in statistical learning.
• Support-vector networks
• Weak convergence and empirical processes. With applications to statistics
• A local maximal inequality under uniform entropy
• The true sample complexity of active learning
• Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
• Rates of convergence in active learning
• Concentration inequalities and asymptotic results for ratio type empirical processes
• Agnostic active learning
• Local Rademacher complexities
• Efficient noise-tolerant learning from statistical queries
• Agnostically Learning Halfspaces
• Minimax Bounds for Active Learning
• Rademacher penalties and structural risk minimization
• 10.1162/1532443041424319
• 10.1162/153244303321897690
• Theory of Disagreement-Based Active Learning
• Information-Based Complexity, Feedback and Dynamics in Convex Programming
• Plug-in Approach to Active Learning
• Activized Learning: Transforming Passive to Active with Improved Label Complexity
• Teaching Dimension and the Complexity of Active Learning
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• Convexity, Classification, and Risk Bounds
• Convergence of stochastic processes
• Introduction to nonparametric estimation

This page was built for publication: Surrogate losses in passive and active learning