A theory of transfer learning with applications to active learning

DOI10.1007/s10994-012-5310-yzbMath1260.68352MaRDI QIDQ1945022

Steve Hanneke, Liu Yang, Jaime G. Carbonell

Publication date: 28 March 2013

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

Full work available at URL: https://figshare.com/articles/journal_contribution/A_Theory_of_Transfer_Learning_with_Applications_to_Active_Learning/6472997

zbMATH Keywords

Bayesian learning; statistical learning theory; active learning; multi-task learning; transfer learning; sample complexity

Mathematics Subject Classification ID

68Q32: Computational learning theory

68T05: Learning and adaptive systems in artificial intelligence

Related Items

Unnamed Item, Bounds on the minimax rate for estimating a prior over a VC class from independent learning tasks, Marginal singularity and the benefits of labels in covariate-shift, A no-free-lunch theorem for multitask learning, Physics-informed neural networks for solving forward and inverse flow problems via the Boltzmann-BGK formulation

Uses Software

• Prodigy

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Rates of convergence of minimum distance estimators and Kolmogorov's entropy
• Estimation of dependences based on empirical data. Transl. from the Russian by Samuel Kotz
• A Bayesian/information theoretic model of learning to learn via multiple task sampling
• Selective sampling using the query by committee algorithm
• Theory of statistics
• The true sample complexity of active learning
• Rates of convergence in active learning
• Agnostic active learning
• 10.1162/153244302760185243
• Active Learning in the Non-realizable Case
• Minimax Bounds for Active Learning
• Learning Theory and Kernel Machines
• Margin Based Active Learning
• Teaching Dimension and the Complexity of Active Learning
• Combinatorial methods in density estimation