Geometry-aware Autoregressive Models for Calorimeter Shower Simulations

• URL: http://arxiv.org/abs/2212.08233v1
• Date: Fri, 16 Dec 2022 01:45:17 GMT
• Title: Geometry-aware Autoregressive Models for Calorimeter Shower Simulations
• Authors: Junze Liu, Aishik Ghosh, Dylan Smith, Pierre Baldi, Daniel Whiteson
• Abstract summary: We develop a geometry-aware autoregressive model on a range of calorimeter geometries. This is a key proof-of-concept step towards building a model that can generalize to new unseen calorimeter geometries. Such a model can replace the hundreds of generative models used for calorimeter simulation in a Large Hadron Collider experiment.
• Score: 6.01665219244256
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Calorimeter shower simulations are often the bottleneck in simulation time for particle physics detectors. A lot of effort is currently spent on optimizing generative architectures for specific detector geometries, which generalize poorly. We develop a geometry-aware autoregressive model on a range of calorimeter geometries such that the model learns to adapt its energy deposition depending on the size and position of the cells. This is a key proof-of-concept step towards building a model that can generalize to new unseen calorimeter geometries with little to no additional training. Such a model can replace the hundreds of generative models used for calorimeter simulation in a Large Hadron Collider experiment. For the study of future detectors, such a model will dramatically reduce the large upfront investment usually needed to generate simulations.

Related papers

• von Mises Quasi-Processes for Bayesian Circular Regression [57.88921637944379]
  We explore a family of expressive and interpretable distributions over circle-valued random functions. The resulting probability model has connections with continuous spin models in statistical physics. For posterior inference, we introduce a new Stratonovich-like augmentation that lends itself to fast Markov Chain Monte Carlo sampling.
  arXiv  Detail & Related papers  (2024-06-19T01:57:21Z)
• Unifying Simulation and Inference with Normalizing Flows [0.08796261172196743]
  We show that two tasks can be unified by using maximum likelihood estimation (MLE) from conditional generative models for energy regression. Using an ATLAS-like calorimeter simulation, we demonstrate this concept in the context of calorimeter energy calibration.
  arXiv  Detail & Related papers  (2024-04-29T18:00:00Z)
• CaloClouds II: Ultra-Fast Geometry-Independent Highly-Granular Calorimeter Simulation [0.0]
  Generative machine learning models have been shown to speed up and augment the traditional simulation chain in physics analysis. A major advancement is the recently introduced CaloClouds model, which generates calorimeter showers as point clouds for the electromagnetic calorimeter of the envisioned International Large Detector (ILD) In this work, we introduce CaloClouds II which features a number of key improvements. This includes continuous time score-based modelling, which allows for a 25-step sampling with comparable fidelity to CaloClouds while yielding a $6times$ speed-up over Geant4 on a single CPU.
  arXiv  Detail & Related papers  (2023-09-11T18:00:02Z)
• Geometric Neural Diffusion Processes [55.891428654434634]
  We extend the framework of diffusion models to incorporate a series of geometric priors in infinite-dimension modelling. We show that with these conditions, the generative functional model admits the same symmetry.
  arXiv  Detail & Related papers  (2023-07-11T16:51:38Z)
• Comparison of Point Cloud and Image-based Models for Calorimeter Fast Simulation [48.26243807950606]
  Two state-of-the-art score based models are trained on the same set of calorimeter simulation and directly compared. generative models are a new class of generative models that have been shown to accurately generate high dimensional calorimeter datasets.
  arXiv  Detail & Related papers  (2023-07-10T08:20:45Z)
• Generalizing to new geometries with Geometry-Aware Autoregressive Models (GAAMs) for fast calorimeter simulation [6.099458999905677]
  Generative models can provide more rapid sample production, but currently require significant effort to optimize performance for specific detector geometries. We develop a $textitgeometry-aware$ autoregressive model, which learns how the calorimeter response varies with geometry. The geometry-aware model outperforms a baseline unaware model by over $50%$ in several metrics.
  arXiv  Detail & Related papers  (2023-05-19T08:54:49Z)
• Automatic Parameterization for Aerodynamic Shape Optimization via Deep Geometric Learning [60.69217130006758]
  We propose two deep learning models that fully automate shape parameterization for aerodynamic shape optimization. Both models are optimized to parameterize via deep geometric learning to embed human prior knowledge into learned geometric patterns. We perform shape optimization experiments on 2D airfoils and discuss the applicable scenarios for the two models.
  arXiv  Detail & Related papers  (2023-05-03T13:45:40Z)
• CaloMan: Fast generation of calorimeter showers with density estimation on learned manifolds [10.089611750812391]
  Most computationally expensive simulations involve calorimeter showers. Deep generative modelling has opened the possibility of generating realistic calorimeter showers orders of magnitude more quickly than physics-based simulation. We propose modelling calorimeter showers first by learning their manifold structure, and then estimating the density of data across this manifold.
  arXiv  Detail & Related papers  (2022-11-23T19:00:03Z)
• Score-based Generative Models for Calorimeter Shower Simulation [2.0813318162800707]
  We introduce CaloScore, a score-based generative model for collider physics applied to calorimeter shower generation. CaloScore is the first application of a score-based generative model in collider physics and is able to produce high-fidelity calorimeter images for all datasets.
  arXiv  Detail & Related papers  (2022-06-17T18:01:02Z)
• Learning Large-scale Subsurface Simulations with a Hybrid Graph Network Simulator [57.57321628587564]
  We introduce Hybrid Graph Network Simulator (HGNS) for learning reservoir simulations of 3D subsurface fluid flows. HGNS consists of a subsurface graph neural network (SGNN) to model the evolution of fluid flows, and a 3D-U-Net to model the evolution of pressure. Using an industry-standard subsurface flow dataset (SPE-10) with 1.1 million cells, we demonstrate that HGNS is able to reduce the inference time up to 18 times compared to standard subsurface simulators.
  arXiv  Detail & Related papers  (2022-06-15T17:29:57Z)
• Machine learning for rapid discovery of laminar flow channel wall modifications that enhance heat transfer [56.34005280792013]
  We present a combination of accurate numerical simulations of arbitrary, flat, and non-flat channels and machine learning models predicting drag coefficient and Stanton number. We show that convolutional neural networks (CNN) can accurately predict the target properties at a fraction of the time of numerical simulations.
  arXiv  Detail & Related papers  (2021-01-19T16:14:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.