Package: sMTL 0.1.0

sMTL: Sparse Multi-Task Learning

Implements L0-constrained Multi-Task Learning and domain generalization algorithms. The algorithms are coded in Julia allowing for fast implementations of the coordinate descent and local combinatorial search algorithms. For more details, see a preprint of the paper: Loewinger et al., (2022) <arxiv:2212.08697>.

Authors:Gabriel Loewinger [aut, cre], Kayhan Behdin [aut], Giovanni Parmigiani [aut], Rahul Mazumder [aut], National Science Foundation Grant DMS1810829 [fnd], National Science Foundation Grant DMS2113707 [fnd], National Science Foundation Grant NSF-IIS1718258, [fnd], Office of Naval Research Grant ONR N000142112841 [fnd], National Institute on Drug Abuse Grant F31DA052153 [fnd]

sMTL_0.1.0.tar.gz
sMTL_0.1.0.zip(r-4.7)sMTL_0.1.0.zip(r-4.6)sMTL_0.1.0.zip(r-4.5)
sMTL_0.1.0.tgz(r-4.6-any)sMTL_0.1.0.tgz(r-4.5-any)
sMTL_0.1.0.tar.gz(r-4.7-any)sMTL_0.1.0.tar.gz(r-4.6-any)
sMTL_0.1.0.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
card.svg |card.png
sMTL/json (API)

# Install 'sMTL' in R:

install.packages('sMTL', repos = c('https://gloewing.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/gloewing/smtl/issues

On CRAN:

1.00 score 8 scripts 195 downloads 16 exports 83 dependencies

Last updated from:2aa7aea46d. Checks:9 OK. Indexed: yes.

Target	Result	Time
linux-devel-x86_64	OK	161
source / vignettes	OK	174
linux-release-x86_64	OK	138
macos-release-arm64	OK	80
macos-oldrel-arm64	OK	104
windows-devel	OK	91
windows-release	OK	125
windows-oldrel	OK	95
wasm-release	OK	119

Exports:cv.smtl grid.gen maxEigen method_nm multiTaskRmse multiTaskRmse_MT predict reName_cv rhoScale seReturn smtl smtl_setup sparseCV sparseCV_MT sparseL0Tn_iht tuneZscale

Dependencies:caret class cli clock codetools cpp11 data.table diagram digest dplyr e1071 evaluate farver foreach future future.apply generics ggplot2 glmnet globals glue gower gtable hardhat highr ipred isoband iterators JuliaCall JuliaConnectoR KernSmooth knitr labeling lattice lava lifecycle listenv lubridate magrittr MASS Matrix ModelMetrics nlme nnet numDeriv parallelly pillar pkgconfig plyr pROC prodlim progressr proxy purrr R6 RColorBrewer Rcpp RcppEigen recipes reshape2 rjson rlang rpart S7 scales shape sparsevctrs SQUAREM stringi stringr survival tibble tidyr tidyselect timechange timeDate tzdb utf8 vctrs viridisLite withr xfun yaml

Help page	Topics
cv.smtl: cross-validation function	cv.smtl
grid.gen: generate grid for cross-validation function. For internal package use only.	grid.gen
maxEigen: maximum eigenvalue wrapper for Julia TSVD package. internal package use only	maxEigen
methods names: give name for printing. Internal package use only.	method_nm
multiTaskRmse: RMSE for multi-task problems (averaged across tasks)	multiTaskRmse
multiTaskRmse: calculate average (across tasks) RMSE for multi-label prediction problems	multiTaskRmse_MT
predict: predict on smtl model object	predict
reName_cv: rename output from CV. For internal package use only.	reName_cv
rhoScale: scale lambda_z depending on magnitude. For internal package use only.	rhoScale
seReturn: find smallest rho within 1 se of smallest cv error. For internal package use.	seReturn
smtl: make model-fitting function	smtl
smtl_setup: setup Julia path and/or install Julia or Julia packages using functions based on external package JuliaCall::julia_setup().	smtl_setup
sparseCV: cross-validation functions. For internal package use only.	sparseCV
sparseCV_MT: internal cross-validation functions. For internal package use only.	sparseCV_MT
sparseCV_L0: cross-validation functions. For internal package use only.	sparseL0Tn_iht
tuneZscale: scale lambda_z depending on magnitude. For internal package use only.	tuneZscale

Package: sMTL 0.1.0

sMTL: Sparse Multi-Task Learning

Citation

Readme and manuals

Help Manual

Usage by other packages (reverse dependencies)