Deep Generative Models for Detector Signature Simulation: A Taxonomic Review

Abstract

In modern collider experiments, the quest to explore fundamental interactions between elementary particles has reached unparalleled levels of precision. Signatures from particle physics detectors are low-level objects (such as energy depositions or tracks) encoding the physics of collisions (the final state particles of hard scattering interactions). The complete simulation of them in a detector is a computational and storage-intensive task. To address this computational bottleneck in particle physics, alternative approaches have been developed, introducing additional assumptions and trade off accuracy for speed.The field has seen a surge in interest in surrogate modeling the detector simulation, fueled by the advancements in deep generative models. These models aim to generate responses that are statistically identical to the observed data. In this paper, we conduct a comprehensive and exhaustive taxonomic review of the existing literature on the simulation of detector signatures from both methodological and application-wise perspectives. Initially, we formulate the problem of detector signature simulation and discuss its different variations that can be unified. Next, we classify the state-of-the-art methods into five distinct categories based on their underlying model architectures, summarizing their respective generation strategies. Finally, we shed light on the challenges and opportunities that lie ahead in detector signature simulation, setting the stage for future research and development.

arXiv commentv2: Accepted in Reviews in Physics

References in corpus (166)

• Conditional Generative Adversarial Nets
• Denoising Diffusion Probabilistic Models
• Practical Bayesian Optimization of Machine Learning Algorithms
• Generative Adversarial Networks
• Neural Message Passing for Quantum Chemistry
• Spectral Normalization for Generative Adversarial Networks
• DELPHES 3, A modular framework for fast simulation of a generic collider experiment
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• Hierarchical Text-Conditional Image Generation with CLIP Latents
• Variational Inference with Normalizing Flows
• Score-Based Generative Modeling through Stochastic Differential Equations
• Generative Modeling by Estimating Gradients of the Data Distribution
• Skillful Precipitation Nowcasting using Deep Generative Models of Radar
• Disentangling by Factorising
• Kernel Estimation in High-Energy Physics
• GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
• Hyper-Kamiokande Design Report
• MMD GAN: Towards Deeper Understanding of Moment Matching Network
• A note on the evaluation of generative models
• CaloGAN: Simulating 3D High Energy Particle Showers in Multi-Layer Electromagnetic Calorimeters with Generative Adversarial Networks
• InfoVAE: Information Maximizing Variational Autoencoders
• Anomaly Detection with Density Estimation
• Elucidating the Design Space of Diffusion-Based Generative Models
• Everything is Connected: Graph Neural Networks
• Classification without labels: Learning from mixed samples in high energy physics
• Learning Particle Physics by Example: Location-Aware Generative Adversarial Networks for Physics Synthesis
• Variational Diffusion Models
• Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multi-Layer Calorimeters
• Searching for New Physics with Deep Autoencoders
• The Cramer Distance as a Solution to Biased Wasserstein Gradients
• Anomaly Detection for Resonant New Physics with Machine Learning
• Energy Flow Networks: Deep Sets for Particle Jets
• Importance Weighted Autoencoders
• Object-Centric Learning with Slot Attention
• Extending the Bump Hunt with Machine Learning
• Progressive Distillation for Fast Sampling of Diffusion Models
• Efficient Graph Generation with Graph Recurrent Attention Networks
• How to GAN LHC Events
• A Cookbook of Self-Supervised Learning
• QCD or What?
• Getting High: High Fidelity Simulation of High Granularity Calorimeters with High Speed
• Novelty Detection Meets Collider Physics
• Adversarially-trained autoencoders for robust unsupervised new physics searches
• Tackling the Generative Learning Trilemma with Denoising Diffusion GANs
• AdaGAN: Boosting Generative Models
• The Lund Jet Plane
• Variational Autoencoders for New Physics Mining at the Large Hadron Collider
• The Dark Machines Anomaly Score Challenge: Benchmark Data and Model Independent Event Classification for the Large Hadron Collider
• Machine Learning and LHC Event Generation
• Uncovering latent jet substructure
• Classifying Anomalies THrough Outer Density Estimation (CATHODE)
• Calorimetry with Deep Learning: Particle Simulation and Reconstruction for Collider Physics
• Score-based Generative Models for Calorimeter Shower Simulation
• Tag N' Train: A Technique to Train Improved Classifiers on Unlabeled Data
• Autoencoders for unsupervised anomaly detection in high energy physics
• ContraGAN: Contrastive Learning for Conditional Image Generation
• Anomaly detection with Convolutional Graph Neural Networks
• Fast and accurate simulation of particle detectors using generative adversarial networks
• Neural Networks for Full Phase-space Reweighting and Parameter Tuning
• DijetGAN: A Generative-Adversarial Network Approach for the Simulation of QCD Dijet Events at the LHC
• How to GAN away Detector Effects
• Unfolding with Generative Adversarial Networks
• How to Train Your Energy-Based Models
• Better Latent Spaces for Better Autoencoders
• Variational Autoencoders for Anomalous Jet Tagging
• Autoencoders on FPGAs for real-time, unsupervised new physics detection at 40 MHz at the Large Hadron Collider
• Event Generators for High-Energy Physics Experiments
• Decoding Photons: Physics in the Latent Space of a BIB-AE Generative Network
• Generative Networks for Precision Enthusiasts
• GANplifying Event Samples
• A robust anomaly finder based on autoencoders
• Bias and Generalization in Deep Generative Models: An Empirical Study
• Bump Hunting in Latent Space
• Controlling Physical Attributes in GAN-Accelerated Simulation of Electromagnetic Calorimeters
• Fast Point Cloud Generation with Diffusion Models in High Energy Physics
• Rare and Different: Anomaly Scores from a combination of likelihood and out-of-distribution models to detect new physics at the LHC
• CaloClouds: Fast Geometry-Independent Highly-Granular Calorimeter Simulation
• Revisiting Classifier Two-Sample Tests
• Sliced-Wasserstein Autoencoder: An Embarrassingly Simple Generative Model
• Evaluating generative models in high energy physics
• Challenges for Unsupervised Anomaly Detection in Particle Physics
• Learning the latent structure of collider events
• Lund jet images from generative and cycle-consistent adversarial networks
• Resonant anomaly detection without background sculpting
• Quasi Anomalous Knowledge: Searching for new physics with embedded knowledge
• Autoencoders for Semivisible Jet Detection
• EPiC-GAN: Equivariant Point Cloud Generation for Particle Jets
• Generative Models for Fast Calorimeter Simulation.LHCb case
• PC-JeDi: Diffusion for Particle Cloud Generation in High Energy Physics
• Online-compatible Unsupervised Non-resonant Anomaly Detection
• L2LFlows: Generating High-Fidelity 3D Calorimeter Images
• Deep Set Auto Encoders for Anomaly Detection in Particle Physics
• Image-based model parameter optimization using Model-Assisted Generative Adversarial Networks
• Particle Transformer for Jet Tagging
• Style-based quantum generative adversarial networks for Monte Carlo events
• FETA: Flow-Enhanced Transportation for Anomaly Detection
• DCTRGAN: Improving the Precision of Generative Models with Reweighting
• Learning to Simulate High Energy Particle Collisions from Unlabeled Data
• Improving Variational Autoencoders for New Physics Detection at the LHC with Normalizing Flows
• How to Understand Limitations of Generative Networks
• DVAE++: Discrete Variational Autoencoders with Overlapping Transformations
• IDF++: Analyzing and Improving Integer Discrete Flows for Lossless Compression
• CaloMan: Fast generation of calorimeter showers with density estimation on learned manifolds
• Natural Graph Networks
• CaloScore v2: Single-shot Calorimeter Shower Simulation with Diffusion Models
• Symmetry meets AI
• SymmetryGAN: Symmetry Discovery with Deep Learning
• Learning the language of QCD jets with transformers
• Edge-based sequential graph generation with recurrent neural networks
• CaloFlow II: Even Faster and Still Accurate Generation of Calorimeter Showers with Normalizing Flows
• The Interplay of Machine Learning--based Resonant Anomaly Detection Methods
• What's Anomalous in LHC Jets?
• Sinkhorn AutoEncoders
• Jet Diffusion versus JetGPT -- Modern Networks for the LHC
• A method to challenge symmetries in data with self-supervised learning
• CaloFlow for CaloChallenge Dataset 1
• Autoencoder-based Anomaly Detection System for Online Data Quality Monitoring of the CMS Electromagnetic Calorimeter
• Black-Box Optimization with Local Generative Surrogates
• High-dimensional and Permutation Invariant Anomaly Detection
• Information bottleneck through variational glasses
• New directions for surrogate models and differentiable programming for High Energy Physics detector simulation
• SARM: Sparse Autoregressive Model for Scalable Generation of Sparse Images in Particle Physics
• Particle-based Fast Jet Simulation at the LHC with Variational Autoencoders
• A Study on the Evaluation of Generative Models
• Comparing Machine Learning and Interpolation Methods for Loop-Level Calculations
• Precision-Machine Learning for the Matrix Element Method
• A semi-supervised approach to dark matter searches in direct detection data with machine learning
• Graph Generative Adversarial Networks for Sparse Data Generation in High Energy Physics
• Compressing PDF sets using generative adversarial networks
• Combining Resonant and Tail-based Anomaly Detection
• DeepRICH: Learning Deeply Cherenkov Detectors
• TraDE: Transformers for Density Estimation
• GAN-AE : An anomaly detection algorithm for New Physics search in LHC data
• Deep Extrapolation for Attribute-Enhanced Generation
• Graph Generative Models for Fast Detector Simulations in High Energy Physics
• Enhancing the hunt for new phenomena in dijet final-states using anomaly detection filters at the High-Luminosity Large Hadron Collider
• Tail-GAN: Learning to Simulate Tail Risk Scenarios
• Polarization measurement for the dileptonic channel of $W^{+}{W}^{-}$ scattering using generative adversarial network
• Graph Neural Networks are Dynamic Programmers
• Toward the End-to-End Optimization of Particle Physics Instruments with Differentiable Programming: a White Paper
• Diffusion Priors In Variational Autoencoders
• Anomaly detection with flow-based fast calorimeter simulators
• Searching for gluon quartic gauge couplings at muon colliders using the auto-encoder
• Non-resonant Anomaly Detection with Background Extrapolation
• Extrapolative Controlled Sequence Generation via Iterative Refinement
• Verifying the Union of Manifolds Hypothesis for Image Data
• PE-GAN: Prior Embedding GAN for PXD images at Belle II
• Generative models uncertainty estimation
• GATSBI: Generative Adversarial Training for Simulation-Based Inference
• Generative Adversarial Networks for Scintillation Signal Simulation in EXO-200
• Branches of a Tree: Taking Derivatives of Programs with Discrete and Branching Randomness in High Energy Physics
• Diffusion Models and Representation Learning: A Survey
• Variational Autoencoders for Generative Modelling of Water Cherenkov Detectors
• Photon detection probability prediction using one-dimensional generative neural network
• Generative Invertible Quantum Neural Networks
• Machine-Learning Compression for Particle Physics Discoveries
• CaloDVAE : Discrete Variational Autoencoders for Fast Calorimeter Shower Simulation
• Geometry-aware Autoregressive Models for Calorimeter Shower Simulations
• CaloQVAE : Simulating high-energy particle-calorimeter interactions using hybrid quantum-classical generative models
• On the Statistical Complexity of Sample Amplification
• Graph Structure and Feature Extrapolation for Out-of-Distribution Generalization
• Morse Neural Networks for Uncertainty Quantification
• Zero-Knowledge Zero-Shot Learning for Novel Visual Category Discovery
• Deep Generative Models for Ultra-High Granularity Particle Physics Detector Simulation: A Voyage From Emulation to Extrapolation
• Synthesis of pulses from particle detectors with a Generative Adversarial Network (GAN)
• A Theoretical Study of Inductive Biases in Contrastive Learning

Cited by in corpus (16)

• Convolutional L2LFlows: Generating Accurate Showers in Highly Granular Calorimeters Using Convolutional Normalizing Flows
• CaloGraph: Graph-based diffusion model for fast shower generation in calorimeters with irregular geometry
• CaloChallenge 2022: A Community Challenge for Fast Calorimeter Simulation
• Calibrating Bayesian Generative Machine Learning for Bayesiamplification
• Unsupervised and lightly supervised learning in particle physics
• Advancing Set-Conditional Set Generation: Diffusion Models for Fast Simulation of Reconstructed Particles
• Parnassus: An Automated Approach to Accurate, Precise, and Fast Detector Simulation and Reconstruction
• Classifier Surrogates: Sharing AI-based Searches with the World
• Foundations of automatic feature extraction at LHC--point clouds and graphs
• Amplitude Uncertainties Everywhere All at Once
• BitHEP -- The Limits of Low-Precision ML in HEP
• CaloHadronic: a diffusion model for the generation of hadronic showers
• ParaFlow: fast calorimeter simulations parameterized in upstream material configurations
• ScatterPrism: convergence for generative simulation and inverse problems in particle and nuclear physics
• CaloClouds3: Ultra-Fast Geometry-Independent Highly-Granular Calorimeter Simulation
• Ultra Fast Calorimeter Simulation with Generative Machine Learning on FPGAs