Functional Decomposition: A new method for search and limit setting

In the analysis of High-Energy Physics data, it is frequently desired to separate resonant signals from a smooth, non-resonant background. This paper introduces a new technique - functional decomposition (FD) - to accomplish this task. It is universal and readily able to describe often-problematic effects such as sculpting and trigger turn-ons. Functional decomposition models a dataset as a truncated series expansion in a complete set of orthonormal basis functions, using a process analogous to Fourier analysis. A new family of orthonormal functions is presented, which has been expressly designed to accomplish this in a succinct way. A consistent signal extraction methodology based on linear signal estimators is also detailed, as is an automated method for selecting the method's (few) hyperparameters and preventing over-fitting. The full collection of algorithms described in this paper have been implemented in an easy-to-use software package, which will also be briefly described.