Variational Pseudo Marginal Methods for Jet Reconstruction in Particle Physics

2024-06-05

arXiv.org

AI Summary

Jet reconstruction in high-energy collider experiments—jointly inferring both the implicit binary-tree topology and physical parameters (e.g., energy, momentum, particle type)—poses a fundamental challenge due to the combinatorially explosive topology space. This paper introduces the first fully Bayesian method that integrates combinatorial sequential Monte Carlo (CSMC) with a variational pseudo-marginal framework. Our approach overcomes the computational intractability of conventional Bayesian inference over super-exponentially growing topologies, enabling end-to-end joint inference of structure and parameters. By leveraging Bayesian generative modeling and pseudo-marginal approximation, it significantly improves both inference efficiency and robustness. Evaluated on simulated collider data, our method outperforms state-of-the-art approaches across multiple metrics—including reconstruction accuracy, topology identification rate, and inference speed—demonstrating superior scalability and statistical fidelity in complex latent-structure inference.

Technology Category

• Machine Learning: Bayesian Learning
• Reasoning under Uncertainty: Relational Probabilistic Models
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

Reconstructing jets, which provide vital insights into the properties and histories of subatomic particles produced in high-energy collisions, is a main problem in data analyses in collider physics. This intricate task deals with estimating the latent structure of a jet (binary tree) and involves parameters such as particle energy, momentum, and types. While Bayesian methods offer a natural approach for handling uncertainty and leveraging prior knowledge, they face significant challenges due to the super-exponential growth of potential jet topologies as the number of observed particles increases. To address this, we introduce a Combinatorial Sequential Monte Carlo approach for inferring jet latent structures. As a second contribution, we leverage the resulting estimator to develop a variational inference algorithm for parameter learning. Building on this, we introduce a variational family using a pseudo-marginal framework for a fully Bayesian treatment of all variables, unifying the generative model with the inference process. We illustrate our method's effectiveness through experiments using data generated with a collider physics generative model, highlighting superior speed and accuracy across a range of tasks.

Problem

• Particle Physics
• Jet Reconstruction
• Bayesian Methods

Innovation

• Sequential Monte Carlo
• Bayesian Framework
• Jet Reconstruction