Jet energy calibration with deep learning as a Kubeflow pipeline

TL;DR

This paper presents a deep learning-based jet energy calibration pipeline built on Kubeflow, improving accuracy and resolution for CMS LHC data, with scalable hyperparameter tuning and deployment.

Contribution

It introduces an end-to-end cloud pipeline for jet energy calibration using deep learning, enabling scalable tuning and deployment of models for high-energy physics.

Findings

Improved jet energy resolution over baseline methods

Enhanced flavor dependence correction

Efficient model serving with low inference overhead

Abstract

Precise measurements of the energy of jets emerging from particle collisions at the LHC are essential for a vast majority of physics searches at the CMS experiment. In this study, we leverage well-established deep learning models for point clouds and CMS open data to improve the energy calibration of particle jets. To enable production-ready machine learning based jet energy calibration an end-to-end pipeline is built on the Kubeflow cloud platform. The pipeline allowed us to scale up our hyperparameter tuning experiments on cloud resources, and serve optimal models as REST endpoints. We present the results of the parameter tuning process and analyze the performance of the served models in terms of inference time and overhead, providing insights for future work in this direction. The study also demonstrates improvements in both flavor dependence and resolution of the energy response when compared to the standard jet energy corrections baseline.