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

arXiv: https://arxiv.org/abs/2306.04712 · HTML: https://mlsanity.com/paper/2306.04712/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 43 references that are in the map.
- First posted on arXiv 7 Jun 2023.

## Builds on (most cited first, 15 of 15)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors](https://mlsanity.com/paper/2006.10159/) (2020)
- [Score-based Generative Models for Calorimeter Shower Simulation](https://mlsanity.com/paper/2206.11898/) (2022)
- [Squared Earth Mover's Distance-based Loss for Training Deep Neural Networks](https://mlsanity.com/paper/1611.05916/) (2016)
- [Particle Cloud Generation with Message Passing Generative Adversarial Networks](https://mlsanity.com/paper/2106.11535/) (2021)
- [Variational Autoencoders for Anomalous Jet Tagging](https://mlsanity.com/paper/2007.01850/) (2020)
- [CaloClouds: Fast Geometry-Independent Highly-Granular Calorimeter Simulation](https://mlsanity.com/paper/2305.04847/) (2023)
- [Evaluating generative models in high energy physics](https://mlsanity.com/paper/2211.10295/) (2022)
- [A reconfigurable neural network ASIC for detector front-end data compression at the HL-LHC](https://mlsanity.com/paper/2105.01683/) (2021)
- [Linearized Optimal Transport for Collider Events](https://mlsanity.com/paper/2008.08604/) (2020)
- [Particle Graph Autoencoders and Differentiable, Learned Energy Mover's Distance](https://mlsanity.com/paper/2111.12849/) (2021)
- [Robust and Provably Monotonic Networks](https://mlsanity.com/paper/2112.00038/) (2021)
- [Finding NEEMo: Geometric Fitting using Neural Estimation of the Energy Mover's Distance](https://mlsanity.com/paper/2209.15624/) (2022)

## Built on by (most cited first, 1 of 1)

- [Variable Rate Neural Compression for Sparse Detector Data](https://mlsanity.com/paper/2411.11942/) (2024)

## Abstract (arXiv)

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.