Reframing Jet Physics with New Computational Methods

TL;DR

This paper introduces a probabilistic framework and new computational methods, including Ginkgo, to improve jet physics tasks such as reconstruction, tuning, and event generation, leveraging techniques from machine learning and optimization.

Contribution

It presents Ginkgo, a generative model for jets, and demonstrates how probabilistic programming, trellis algorithms, and reinforcement learning can enhance jet analysis tasks.

Findings

Efficient sampling of the showering process using probabilistic programming.

Novel trellis algorithm for marginalizing clustering histories.

Application of dynamic programming and reinforcement learning for maximum likelihood clustering.

Abstract

We reframe common tasks in jet physics in probabilistic terms, including jet reconstruction, Monte Carlo tuning, matrix element - parton shower matching for large jet multiplicity, and efficient event generation of jets in complex, signal-like regions of phase space. We also introduce Ginkgo, a simplified, generative model for jets, that facilitates research into these tasks with techniques from statistics, machine learning, and combinatorial optimization. We review some of the recent research in this direction that has been enabled with Ginkgo. We show how probabilistic programming can be used to efficiently sample the showering process, how a novel trellis algorithm can be used to efficiently marginalize over the enormous number of clustering histories for the same observed particles, and how dynamic programming, A* search, and reinforcement learning can be used to find the maximum likelihood clustering in this enormous search space. This work builds bridges with work in hierarchical clustering, statistics, combinatorial optmization, and reinforcement learning.