Autoencoders for Real-Time SUEP Detection
- URL: http://arxiv.org/abs/2306.13595v3
- Date: Fri, 5 Jul 2024 11:34:10 GMT
- Title: Autoencoders for Real-Time SUEP Detection
- Authors: Simranjit Singh Chhibra, Nadezda Chernyavskaya, Benedikt Maier, Maurzio Pierini, Syed Hasan,
- Abstract summary: We develop a deep learning-based Anomaly Detection technique to reject QCD jets and identify any anomalous signature.
A convolutional neural autoencoder network has been trained using QCD events by taking transverse energy deposits.
The trained model can be applied to any new physics model that predicts an experimental signature anomalous to QCD jets.
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Confining dark sectors with pseudo-conformal dynamics can produce Soft Unclustered Energy Patterns (SUEP), at the Large Hadron Collider: the production of dark quarks in proton-proton collisions leading to a dark shower and the high-multiplicity production of dark hadrons. The final experimental signature is spherically-symmetric energy deposits by an anomalously large number of soft Standard Model particles with a transverse energy of O(100) MeV. Assuming Yukawa-like couplings of the scalar portal state, the dominant production mode is gluon fusion, and the dominant background comes from multi-jet QCD events. We have developed a deep learning-based Anomaly Detection technique to reject QCD jets and identify any anomalous signature, including SUEP, in real-time in the High-Level Trigger system of the Compact Muon Solenoid experiment at the Large Hadron Collider. A deep convolutional neural autoencoder network has been trained using QCD events by taking transverse energy deposits in the inner tracker, electromagnetic calorimeter, and hadron calorimeter sub-detectors as 3-channel image data. Due to the sparse nature of the data, only ~0.5% of the total ~300 k image pixels have non-zero values. To tackle this challenge, a non-standard loss function, the inverse of the so-called Dice Loss, is exploited. The trained autoencoder with learned spatial features of QCD jets can detect 40% of the SUEP events, with a QCD event mistagging rate as low as 2%. The model inference time has been measured using the Intel CoreTM i5-9600KF processor and found to be ~20 ms, which perfectly satisfies the High-Level Trigger system's latency of O(100) ms. Given the virtue of the unsupervised learning of the autoencoders, the trained model can be applied to any new physics model that predicts an experimental signature anomalous to QCD jets.
Related papers
- A Comparison of Deep Learning Models for Proton Background Rejection
with the AMS Electromagnetic Calorimeter [0.0]
The Alpha Magnetic Spectrometer (AMS) is a high-precision particle detector onboard the International Space Station.
The positron flux measured in space by AMS falls with a power law which unexpectedly softens above 25 GeV and then hardens above 280 GeV.
We present a new approach for particle identification with the AMS ECAL using deep learning (DL)
arXiv Detail & Related papers (2024-02-26T04:06:05Z) - Design and simulation of a transmon qubit chip for Axion detection [103.69390312201169]
Device based on superconducting qubits has been successfully applied in detecting few-GHz single photons via Quantum Non-Demolition measurement (QND)
In this study, we present Qub-IT's status towards the realization of its first superconducting qubit device.
arXiv Detail & Related papers (2023-10-08T17:11:42Z) - Quantized Non-Volatile Nanomagnetic Synapse based Autoencoder for
Efficient Unsupervised Network Anomaly Detection [0.07892577704654172]
We show that implementing the autoencoder in edge devices capable of learning in real-time is challenging due to limited hardware, energy, and computational resources.
We propose a ferromagnetic racetrack with engineered notches hosting a magnetic domain wall (DW) as the autoencoder synapses.
Our DW-based approach demonstrates a remarkable reduction of at least three orders of magnitude in weight updates during training compared to the floating-point approach.
arXiv Detail & Related papers (2023-09-12T02:29:09Z) - Towards Neural Variational Monte Carlo That Scales Linearly with System
Size [67.09349921751341]
Quantum many-body problems are central to demystifying some exotic quantum phenomena, e.g., high-temperature superconductors.
The combination of neural networks (NN) for representing quantum states, and the Variational Monte Carlo (VMC) algorithm, has been shown to be a promising method for solving such problems.
We propose a NN architecture called Vector-Quantized Neural Quantum States (VQ-NQS) that utilizes vector-quantization techniques to leverage redundancies in the local-energy calculations of the VMC algorithm.
arXiv Detail & Related papers (2022-12-21T19:00:04Z) - Long-Range Zero-Shot Generative Deep Network Quantization [46.67334554503704]
Quantization approximates a deep network model with floating-point numbers by the one with low bit width numbers.
We propose a novel deep network quantizer, dubbed Long-Range Zero-Shot Generative Deep Network Quantization (LRQ)
arXiv Detail & Related papers (2022-11-13T04:43:52Z) - Validation tests of GBS quantum computers give evidence for quantum
advantage with a decoherent target [62.997667081978825]
We use positive-P phase-space simulations of grouped count probabilities as a fingerprint for verifying multi-mode data.
We show how one can disprove faked data, and apply this to a classical count algorithm.
arXiv Detail & Related papers (2022-11-07T12:00:45Z) - Collider Events on a Quantum Computer [0.0]
We present a novel approach to synthesising parton showers using the Discrete QCD method.
This is the first time a Noisy Intermediate-Scale Quantum (NISQ) device has been used to simulate realistic high-energy particle collision events.
arXiv Detail & Related papers (2022-07-21T18:07:22Z) - A Probabilistic Autoencoder for Type Ia Supernovae Spectral Time Series [1.3316902142331577]
We construct a probabilistic autoencoder to learn the intrinsic diversity of type Ia supernovae (SNe Ia) from a sparse set of spectral time series.
We show that the PAE learns a low-dimensional latent space that captures the nonlinear range of features that exists within the population.
We then use our PAE in a number of downstream tasks on SNe Ia for increasingly precise cosmological analyses.
arXiv Detail & Related papers (2022-07-15T17:58:27Z) - A reconfigurable neural network ASIC for detector front-end data
compression at the HL-LHC [0.40690419770123604]
A neural network autoencoder model can be implemented in a radiation tolerant ASIC to perform lossy data compression.
This is the first radiation tolerant on-detector ASIC implementation of a neural network that has been designed for particle physics applications.
arXiv Detail & Related papers (2021-05-04T18:06:23Z) - Autoencoders for unsupervised anomaly detection in high energy physics [105.54048699217668]
We study the tagging of top jet images in a background of QCD jet images.
We show that the standard autoencoder setup cannot be considered as a model-independent anomaly tagger.
We suggest improved performance measures for the task of model-independent anomaly detection.
arXiv Detail & Related papers (2021-04-19T05:06:57Z) - Hardware-efficient error-correcting codes for large nuclear spins [62.997667081978825]
We present a hardware-efficient quantum protocol that corrects phase flips of a nuclear spin using explicit experimentally feasible operations.
Results provide a realizable blueprint for a corrected spin-based qubit.
arXiv Detail & Related papers (2021-03-15T17:14:48Z)
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.