RootInteractive tool for multidimensional statistical analysis, machine learning and analytical model validation

Abstract

The ALICE experiment [1] at CERN’s LHC is specifically designed for investigating heavy ion collisions. The upgraded ALICE accommodates a tenfold increase in Pb–Pb luminosity and a two-order-of-magnitude surge in minimum bias events. To address the challenges of high detector occupancy and event pile-ups, advanced multidimensional data analysis techniques, including machine learning (ML), are indispensable. Despite ML’s popularity, the complexity of its models presents interpretation challenges, and oversimplification in analysis often leads to inaccuracies. Our objective was to develop RootInteractive, a tool for multidimensional statistical analysis. This tool simplifies data analysis across dimensions, visualizes functions with uncertainties, and validates assumptions and approximations. In RootInteractive, it is crucial to easily define the functional composition of analytical parametric and non-parametric functions, exploit symmetries, and define multidimensional "invariant" functions and corresponding alarms. RootInteractive [2] adopts a declarative programming paradigm, ensuring userfriendliness for experts, students, and educators. It facilitates interactive visualization, n-dimensional histogramming/projection, and information extraction on both Python/C++ server and Javascript client. The tool supports client/server applications in Jupyter or standalone client-side applications. Through data compression, datasets with O(107) entries and O(25) attributes can be interactively analyzed in a browser with O(0.500-1 GB) size. Representative downsampling and reweighting/pre-aggregation enable the effective analysis of one year of ALICE data for various purposes.