Triggering Dark Showers with Conditional Dual Auto-Encoders
arXiv:2306.12955 · doi:10.1088/2632-2153/ad652b
Abstract
We present a family of conditional dual auto-encoders (CoDAEs) for generic and model-independent new physics searches at colliders. New physics signals, which arise from new types of particles and interactions, are considered in our study as anomalies causing deviations in data with respect to expected background events. In this work, we perform a normal-only anomaly detection, which employs only background samples, to search for manifestations of a dark version of strong force applying (variational) auto-encoders on raw detector images, which are large and highly sparse, without leveraging any physics-based pre-processing or strong assumption on the signals. The proposed CoDAE has a dual-encoder design, which is general and can learn an auxiliary yet compact latent space through spatial conditioning, showing a neat improvement over competitive physics-based baselines and related approaches, therefore also reducing the gap with fully supervised models. It is the first time an unsupervised model is shown to exhibit excellent discrimination against multiple dark shower models, illustrating the suitability of this method as an accurate, fast, model-independent algorithm to deploy, e.g., in the real-time event triggering systems of Large Hadron Collider experiments such as ATLAS and CMS.
24 pages, 6 figures, and 4 tables; journal version
References in corpus (38)
- Auto-Encoding Variational Bayes
- Observation of a new boson at a mass of 125 GeV with the CMS experiment at the LHC
- Decoupled Weight Decay Regularization
- Conditional Generative Adversarial Nets
- An Introduction to PYTHIA 8.2
- Categorical Reparameterization with Gumbel-Softmax
- Asymptotic formulae for likelihood-based tests of new physics
- Instance Normalization: The Missing Ingredient for Fast Stylization
- DELPHES 3, A modular framework for fast simulation of a generic collider experiment
- Deep Learning for Anomaly Detection: A Survey
- Searching for Exotic Particles in High-Energy Physics with Deep Learning
- The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
- Particle-flow reconstruction and global event description with the CMS detector
- Echoes of a Hidden Valley at Hadron Colliders
- The CMS trigger system
- Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders
- Classification without labels: Learning from mixed samples in high energy physics
- Escaping the Big Data Paradigm with Compact Transformers
- The Machine Learning Landscape of Top Taggers
- Quirky Composite Dark Matter
- Semi-visible Jets: Dark Matter Undercover at the LHC
- QCD or What?
- LHC Searches for Dark Sector Showers
- Autoencoders for unsupervised anomaly detection in high energy physics
- Triggering Soft Bombs at the LHC
- 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
- Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEs
- Bump Hunting in Latent Space
- Challenges for Unsupervised Anomaly Detection in Particle Physics
- Autoencoders for Semivisible Jet Detection
- Symmetries, Safety, and Self-Supervision
- Self-supervised Anomaly Detection for New Physics
- Anomaly Detection under Coordinate Transformations
- deep-significance - Easy and Meaningful Statistical Significance Testing in the Age of Neural Networks
- Exploring Jet Substructure in Semi-visible jets
- Improving Parametric Neural Networks for High-Energy Physics (and Beyond)