Generator Based Inference (GBI)

TL;DR

This paper introduces Generator Based Inference (GBI), a framework integrating machine learning with generators for physics data analysis, enabling improved anomaly detection and parameter estimation using data-driven generators.

Contribution

It generalizes simulation-based inference by incorporating data-driven generators, especially for resonant anomaly detection, and demonstrates state-of-the-art performance on benchmark datasets.

Findings

Achieves new state-of-the-art anomaly detection sensitivity.

Provides a method for machine learning-based parameter estimation with data-derived generators.

Transforms anomaly detection outputs into directly interpretable statistical measures.

Abstract

Statistical inference in physics is often based on samples from a generator (sometimes referred to as a ``forward model") that emulate experimental data and depend on parameters of the underlying theory. Modern machine learning has supercharged this workflow to enable high-dimensional and unbinned analyses to utilize much more information than ever before. We propose a general framework for describing the integration of machine learning with generators called Generator Based Inference (GBI). A well-studied special case of this setup is Simulation Based Inference (SBI) where the generator is a physics-based simulator. In this work, we examine other methods within the GBI toolkit that use data-driven methods to build the generator. In particular, we focus on resonant anomaly detection, where the generator describing the background is learned from sidebands. We show how to perform machine learning-based parameter estimation in this context with data-derived generators. This transforms the statistical outputs of anomaly detection to be directly interpretable and the performance on the LHCO community benchmark dataset establishes a new state-of-the-art for anomaly detection sensitivity.