Risk bound of transfer learning using parametric feature mapping and its application to sparse coding

DOI10.1007/S10994-019-05805-2MaRDI QIDQ2331678zbMATH OpenOpenAlexFDO

Authors Wataru Kumagai, Takafumi Kanamori

Publication date 30 October 2019

Published in Machine Learning (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1007/s10994-019-05805-2

zbMATH Keywords

risk boundsparse codingtransfer learning

Mathematics Subject Classification ID

Point estimation (62F10) Ridge regression; shrinkage estimators (Lasso) (62J07) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Transfer bounds for linear feature learning
• A theoretical framework for deep transfer learning
• A theory of transfer learning with applications to active learning
• On Universal Transfer Learning
• On universal transfer learning

Cites work

• Deep learning
• Fast rates by transferring from auxiliary hypotheses
• scientific article; zbMATH DE number 5957408 (Why is no real title available?)
• scientific article; zbMATH DE number 5547839 (Why is no real title available?)
• scientific article; zbMATH DE number 1448976 (Why is no real title available?)
• Improving predictive inference under covariate shift by weighting the log-likelihood function
• On Sparse Representations in Arbitrary Redundant Bases
• Online learning for matrix factorization and sparse coding
• Self-taught dimensionality reduction on the high-dimensional small-sized data
• The Lasso problem and uniqueness
• The sample complexity of dictionary learning
• Transfer bounds for linear feature learning

Cited in

(1)

• Mitigating barren plateaus with transfer-learning-inspired parameter initializations

Describes a project that uses

Uses Software

• R
• Kernlab

This page was built for publication: Risk bound of transfer learning using parametric feature mapping and its application to sparse coding

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2331678)