Home

Welcome to the MT_GB wiki!

The provided algorithm contains an implementation of the Multi-Task Gradient Boosting (MT-GB) algorithm, which extends the popular Gradient Boosting method for both classification and regression problems. The MT-GB algorithm is a supervised learning technique that aims to predict multiple related tasks simultaneously. The implementation is based on the scikit-learn and provides additional functionality specific to MT-GB, such as the ability to predict multiple related targets and the inclusion of a metric to evaluate the quality of the model on multiple tasks. The wiki page for this code includes information on how to use the algorithm, examples of how to run the code on toy datasets, and a detailed explanation of the algorithm's underlying principles.