Package: orthoMTL 0.1.0

Kevin Vervier

orthoMTL: Multi-Task Learning with Orthogonal Constraints

Fits regularised multi-task learning models where relationships between tasks are controlled via orthogonality or disjoint-support constraints. Supports regression, binary classification, and censored survival data. In survival mode, time-to-event outcomes are converted into binary labels at user-defined thresholds, enabling the discovery of features with time-varying effects that standard proportional-hazards models cannot detect. Implements the penalty described in Vervier et al. (2014) <https://hal.science/hal-00985654>.

Authors:Kevin Vervier [aut, cre], Novartis Pharma AG [cph, fnd]

orthoMTL_0.1.0.tar.gz
orthoMTL_0.1.0.zip(r-4.7-any)orthoMTL_0.1.0.zip(r-4.6-any)orthoMTL_0.1.0.zip(r-4.5-any)
orthoMTL_0.1.0.tgz(r-4.6-any)orthoMTL_0.1.0.tgz(r-4.5-any)
orthoMTL_0.1.0.tar.gz(r-4.7-any)orthoMTL_0.1.0.tar.gz(r-4.6-any)
orthoMTL_0.1.0.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
orthoMTL/json (API)

# Install 'orthoMTL' in R:

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

Bug tracker:https://github.com/novartis/orthomtl/issues

On CRAN:

feature-selection machine-learning multi-task-learning sparse-learning structured-learning survival-analysis

4.92 score 2 stars 12 scripts 260 downloads 17 exports 21 dependencies

Last updated from:87dd2a73f7. Checks:9 OK. Indexed: yes.

Target	Result	Time
linux-devel	OK	120
source / vignettes	OK	330
linux-release	OK	143
macos-release	OK	130
macos-oldrel	OK	113
windows-devel	OK	96
windows-release	OK	122
windows-oldrel	OK	89
wasm-release	OK	133

Exports:accuracy_mtl auc_mtl bootstrap_orthoMTL cindex_mtl create_constraint_matrix create_indicator_matrix create_longitudinal_labels cv_orthoMTL nnmaxheap_C orthoMTL plot_bootstrap plot_correlation plot_heatmap plot_prediction r2_mtl rmse_mtl simulate_mtl

Dependencies:cli codetools cpp11 doParallel farver foreach ggplot2 glue gtable isoband iterators labeling lifecycle R6 RColorBrewer rlang S7 scales vctrs viridisLite withr

Introduction to orthoMTL: Multi-Task Survival Analysis

Rendered fromintroduction.Rmdusingknitr::rmarkdown

Last update: 2026-07-10
Started: 2026-06-01

Help page	Topics
Classification Accuracy for Multi-Task Predictions	accuracy_mtl
Area Under the ROC Curve for Multi-Task Predictions	auc_mtl
Bootstrap Inference for orthoMTL Coefficients	bootstrap_orthoMTL
Concordance Index for Multi-Task Predictions	cindex_mtl
Extract Coefficients from an orthoMTL Model	coef.orthoMTL
Create Diffusion Constraint Matrix	create_constraint_matrix
Create Censoring Indicator Matrix	create_indicator_matrix
Convert Survival Data to Longitudinal Binary Labels	create_longitudinal_labels
Cross-Validation for orthoMTL Hyperparameter Selection	cv_orthoMTL
Project a Vector onto Non-Negative Non-Increasing Space	nnmaxheap_C
Multi-task learning with orthogonal constraints	orthoMTL
Bootstrap Coefficient Comparison Plot	plot_bootstrap
Task Correlation Map for orthoMTL	plot_correlation
Coefficient Heatmap for orthoMTL	plot_heatmap
Prediction Swimmer Plot for orthoMTL	plot_prediction
Predict from an orthoMTL Model	predict.orthoMTL
Print Bootstrap Inference Results	print.bootstrap_orthoMTL
Print Cross-Validation Results	print.cv_orthoMTL
Print an orthoMTL Object	print.orthoMTL
Print Simulated Multi-Task Data	print.simulated_mtl
Coefficient of Determination (R-squared) for Multi-Task Regression	r2_mtl
Root Mean Squared Error for Multi-Task Regression	rmse_mtl
Simulate Multi-Task Data with Time-Varying Effects	simulate_mtl
Summarise an orthoMTL Object	summary.orthoMTL

Package: orthoMTL 0.1.0

orthoMTL: Multi-Task Learning with Orthogonal Constraints

Citation

Development and contributors

Readme and manuals

Help Manual

Usage by other packages (reverse dependencies)