Machine Learning Project: Multi-target Regression for Particle Physics

Toolkit for Multivariate Data Analysis (TMVA) is a multi-purpose machine learning toolkit integrated into the ROOT scientific software network, used in many particle physics data analysis and applications. Current implementations of TMVA have expanded regression from the single-target level to the multi-target level, yet only restricted to two certain types of regression. In order to fully accommodate the need for a well-supported, robust multi-target regression framework for particle physicists, this summer we are expanding the toolkit capabilities to cover multi-objective function estimation from more diverse algorithmic approaches.