DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Differentiable Earth mover’s distance for data compression at the high-luminosity LHC

Journal Article · · Machine Learning: Science and Technology

The Earth mover’s distance (EMD) is a useful metric for image recognition and classification, but its usual implementations are not differentiable or too slow to be used as a loss function for training other algorithms via gradient descent. In this paper, we train a convolutional neural network (CNN) to learn a differentiable, fast approximation of the EMD and demonstrate that it can be used as a substitute for computing-intensive EMD implementations. We apply this differentiable approximation in the training of an autoencoder-inspired neural network (encoder NN) for data compression at the high-luminosity LHC at CERN The goal of this encoder NN is to compress the data while preserving the information related to the distribution of energy deposits in particle detectors. We demonstrate that the performance of our encoder NN trained using the differentiable EMD CNN surpasses that of training with loss functions based on mean squared error.

Research Organization:
Fermi National Accelerator Laboratory (FNAL), Batavia, IL (United States)
Sponsoring Organization:
USDOE Office of Science (SC), High Energy Physics (HEP); USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR); National Science Foundation (NSF); USDOE
Grant/Contract Number:
AC02-07CH11359; SC0021187; 2117997; FOA-0002501
OSTI ID:
2251545
Alternate ID(s):
OSTI ID: 1984949; OSTI ID: 2222950
Report Number(s):
FERMILAB-PUB-23-288-CMS-CSAID; arXiv:2306.04712; oai:inspirehep.net:2667126
Journal Information:
Machine Learning: Science and Technology, Vol. 4, Issue 4; ISSN 2632-2153
Publisher:
IOP PublishingCopyright Statement
Country of Publication:
United States
Language:
English

References (22)

The Earth Mover's Distance as a Metric for Image Retrieval journal November 2000
Differential Earth Mover's Distance with Its Applications to Visual Tracking journal February 2010
An Optimal Transportation Approach for Nuclear Structure-Based Pathology journal October 2010
Metric Space of Collider Events journal July 2019
Exploring the space of jets with CMS open data journal February 2020
A robust measure of event isotropy at colliders journal August 2020
Variational autoencoders for anomalous jet tagging journal January 2023
Use of a generalized energy Mover’s distance in the search for rare phenomena at colliders journal February 2021
DeepEMD: Few-Shot Image Classification With Differentiable Earth Mover’s Distance and Structured Classifiers conference June 2020
Linearized optimal transport for collider events journal December 2020
SHAPER: can you hear the shape of a jet? journal June 2023
A spectral metric for collider geometry journal August 2023
Performance of the CMS Level-1 trigger in proton-proton collisions at √ s = 13 TeV journal October 2020
Operation of the ATLAS trigger system in Run 2 journal October 2020
Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors journal June 2021
Geant4—a simulation toolkit
  • Agostinelli, S.; Allison, J.; Amako, K.
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 506, Issue 3 https://doi.org/10.1016/S0168-9002(03)01368-8
journal July 2003
Robust Estimation of a Location Parameter journal March 1964
Evaluating generative models in high energy physics journal April 2023
Score-based generative models for calorimeter shower simulation journal November 2022
CaloClouds: fast geometry-independent highly-granular calorimeter simulation journal November 2023
Toward the end-to-end optimization of particle physics instruments with differentiable programming journal June 2023
CMS High Granularity Calorimeter Trigger Cell Simulated Dataset (Part 1) dataset January 2023