Multi-task and lifelong learning of kernels

DOI10.1007/978-3-319-24486-0_13zbMATH Open1471.68223arXiv1602.06531OpenAlexW2963112576MaRDI QIDQ2835628FDOQ2835628

Authors: Anastasia Pentina, Shai Ben-David 

Publication date: 30 November 2016

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

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.

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

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

zbMATH Keywords

multi-task learninglifelong learningkernel learning

Mathematics Subject Classification ID

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

Cites Work

• Transfer bounds for linear feature learning
• Neural Network Learning
• Convex multi-task feature learning
• Title not available (Why is that?)
• Algorithms for learning kernels based on centered alignment
• Learning Bounds for Support Vector Machines with Learned Kernels
• On the convergence rate of \(l_{p}\)-norm multiple kernel learning
• Covering numbers for real-valued function classes
• Multitask sparsity via maximum entropy discrimination

Cited In (10)

• Multikernel Passive Stochastic Gradient Algorithms and Transfer Learning
• Local Rademacher complexity-based learning guarantees for multi-task learning
• Title not available (Why is that?)
• Learning multiple tasks with kernel methods
• Towards knowledgeable supervised lifelong learning systems
• Lifelong learning in costly feature spaces
• Title not available (Why is that?)
• Multi-task kernel learning based on probabilistic Lipschitzness
• A kernel approach to multi-task learning with task-specific kernels
• Lifelong learning in costly feature spaces

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)