Multi-task and lifelong learning of kernels

DOI10.1007/978-3-319-24486-0_13MaRDI QIDQ2835628zbMATH OpenOpenAlexFDO

Authors Anastasia Pentina, Shai Ben-David

Publication date 30 November 2016

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1602.06531

zbMATH Keywords

kernel learninglifelong learningmulti-task learning

Mathematics Subject Classification ID

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

Abstract: We consider a problem of learning kernels for use in SVM classification in the multi-task and lifelong scenarios and provide generalization bounds on the error of a large margin classifier. Our results show that, under mild conditions on the family of kernels used for learning, solving several related tasks simultaneously is beneficial over single task learning. In particular, as the number of observed tasks grows, assuming that in the considered family of kernels there exists one that yields low approximation error on all tasks, the overhead associated with learning such a kernel vanishes and the complexity converges to that of learning when this good kernel is given to the learner.

Recommendations

• Learning multiple tasks with kernel methods
• A kernel approach to multi-task learning with task-specific kernels
• Multi-task kernel learning based on probabilistic Lipschitzness
• Learning Theory and Kernel Machines
• A notion of task relatedness yielding provable multiple-task learning guarantees

Cites work

• Algorithms for learning kernels based on centered alignment
• Convex multi-task feature learning
• Covering numbers for real-valued function classes
• scientific article; zbMATH DE number 1448976 (Why is no real title available?)
• Learning Bounds for Support Vector Machines with Learned Kernels
• Multitask sparsity via maximum entropy discrimination
• Neural Network Learning
• On the convergence rate of \(l_{p}\)-norm multiple kernel learning
• Transfer bounds for linear feature learning

Cited in

(10)

• Lifelong learning in costly feature spaces
• A kernel approach to multi-task learning with task-specific kernels
• Learning multiple tasks with kernel methods
• scientific article; zbMATH DE number 5957287 (Why is no real title available?)
• scientific article; zbMATH DE number 5968915 (Why is no real title available?)
• Local Rademacher complexity-based learning guarantees for multi-task learning
• Multi-task kernel learning based on probabilistic Lipschitzness
• Lifelong learning in costly feature spaces
• Multikernel Passive Stochastic Gradient Algorithms and Transfer Learning
• Towards knowledgeable supervised lifelong learning systems

This page was built for publication: Multi-task and lifelong learning of kernels

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2835628)