no code implementations • 7 Jun 2023 • Rohan Shenoy, Javier Duarte, Christian Herwig, James Hirschauer, Daniel Noonan, Maurizio Pierini, Nhan Tran, Cristina Mantilla Suarez
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.