Differentiable Earth Mover's Distance for Data Compression at the High-Luminosity LHC

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...

Descripción completa

Detalles Bibliográficos
Autores principales: Shenoy, Rohan, Duarte, Javier, Herwig, Christian, Hirschauer, James, Noonan, Daniel, Pierini, Maurizio, Tran, Nhan, Mantilla Suarez, Cristina
Lenguaje:eng
Publicado: 2023
Materias:
physics.ins-det
Detectors and Experimental Techniques
cs.LG
Computing and Computers
hep-ex
Particle Physics - Experiment
Acceso en línea:http://cds.cern.ch/record/2861959

Internet

http://cds.cern.ch/record/2861959

Ejemplares similares