matrans: Model Averaging-Assisted Optimal Transfer Learning

Transfer learning, as a prevailing technique in computer sciences, aims to improve the performance of a target model by leveraging auxiliary information from heterogeneous source data. We provide novel tools for multi-source transfer learning under statistical models based on model averaging strategies, including linear regression models, partially linear models. Unlike existing transfer learning approaches, this method integrates the auxiliary information through data-driven weight assignments to avoid negative transfer. This is the first package for transfer learning based on the optimal model averaging frameworks, providing efficient implementations for practitioners in multi-source data modeling. The details are described in Hu and Zhang (2023) <https://jmlr.org/papers/v24/23-0030.html>.

Version: 0.1.0
Depends: R (≥ 2.10)
Imports: caret, formatR, MASS, quadprog, splines, stats
Suggests: knitr, rmarkdown
Published: 2024-01-12
Author: Xiaonan Hu ORCID iD [aut, cre], Xinyu Zhang [aut]
Maintainer: Xiaonan Hu <xiaonanhu at cnu.edu.cn>
License: GPL (≥ 3)
NeedsCompilation: no
Materials: README
CRAN checks: matrans results

Documentation:

Reference manual: matrans.pdf
Vignettes: matrans-vignette

Downloads:

Package source: matrans_0.1.0.tar.gz
Windows binaries: r-devel: matrans_0.1.0.zip, r-release: matrans_0.1.0.zip, r-oldrel: matrans_0.1.0.zip
macOS binaries: r-release (arm64): matrans_0.1.0.tgz, r-oldrel (arm64): matrans_0.1.0.tgz, r-release (x86_64): matrans_0.1.0.tgz

Linking:

Please use the canonical form https://CRAN.R-project.org/package=matrans to link to this page.