Differentiable Earth Mover's Distance for Data Compression at the High-Luminosity LHC
This addresses data compression challenges in particle physics experiments, but is incremental as it adapts an existing metric for a specific application.
The paper tackled the problem of making the Earth mover's distance (EMD) differentiable and fast for use as a loss function, by training a convolutional neural network to approximate it, and applied this to data compression at the high-luminosity LHC, showing that it outperforms mean squared error-based training.
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.