A notion of task relatedness yielding provable multiple-task learning guarantees

DOI10.1007/S10994-007-5043-5MaRDI QIDQ1009297zbMATH OpenOpenAlexFDO

Authors Shai Ben-David, Reba Schuller Borbely

Publication date 31 March 2009

Published in Machine Learning (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s10994-007-5043-5

zbMATH Keywords

learning theorymulti-task learningVC-dimensiongeneralization boundsclassification predictioninductive transfertask relatedness

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Computational learning theory (68Q32)

Recommendations

• Learning Theory and Kernel Machines
• Learning multiple tasks with kernel methods
• Bounds for linear multi-task learning
• A Bayesian/information theoretic model of learning to learn via multiple task sampling
• The benefit of multitask representation learning

Cites work

• scientific article; zbMATH DE number 1448976 (Why is no real title available?)
• Learnability and the Vapnik-Chervonenkis dimension
• Learning Theory and Kernel Machines
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities

Cited in

(11)

• A case study on meta-generalising: a Gaussian processes approach
• A no-free-lunch theorem for multitask learning
• Local Rademacher complexity-based learning guarantees for multi-task learning
• Learning Theory and Kernel Machines
• Multi-task and lifelong learning of kernels
• A Bayesian/information theoretic model of learning to learn via multiple task sampling
• Multi-task kernel learning based on probabilistic Lipschitzness
• Bounds for linear multi-task learning
• Metric-guided multi-task learning
• Inductive Logic Programming
• Least square regularized regression for multitask learning

This page was built for publication: A notion of task relatedness yielding provable multiple-task learning guarantees

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1009297)