Differentiable Earth mover’s distance for data compression at the high-luminosity LHC
- Univ. of California, San Diego, La Jolla, CA (United States)
- Fermi National Accelerator Laboratory (FNAL), Batavia, IL (United States)
- European Organization for Nuclear Research (CERN), Geneva (Switzerland)
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
Similar Records
A Reconfigurable Neural Network ASIC for Detector Front-End Data Compression at the HL-LHC
Integrate Light-Weight Deep Learning Tools with Internet of Things