Adversarially Learned Anomaly Detection on CMS Open Data: re-discovering the top quark

  title={Adversarially Learned Anomaly Detection on CMS Open Data: re-discovering the top quark},
  author={Oliver Knapp and Guenther Dissertori and Olmo Cerri and Thong Q. Nguyen and J. R. Vlimant and Maurizio Pierini},
We apply an Adversarially Learned Anomaly Detection (ALAD) algorithm to the problem of detecting new physics processes in proton–proton collisions at the Large Hadron Collider. Anomaly detection based on ALAD matches performances reached by Variational Autoencoders, with a substantial improvement in some cases. Training the ALAD algorithm on 4.4 fb$$^{-1}$$ - 1 of 8 TeV CMS Open Data, we show how a data-driven anomaly detection and characterization would work in real life, re… 
Simulation-assisted decorrelation for resonant anomaly detection
This work studies the robustness of Simulation Ass Likelihood-free Anomaly Detection (SALAD) to correlations between the classifier and the invariant mass and proposes a new approach that only uses the simulation for decorrelation but the Classification without Labels (CWoLa) approach for achieving signal sensitivity.
Learning the latent structure of collider events
An unsupervised machine-learning technique based on the probabilistic (Bayesian) generative model of Latent Dirichlet Allocation is described, which is paired with an approximate inference algorithm called Variational Inference to extract the latent probability distributions describing the learned underlying structure of collider events.
Getting High: High Fidelity Simulation of High Granularity Calorimeters with High Speed
This work investigates the use of a new architecture—the Bounded Information Bottleneck Autoencoder—for modelling electromagnetic showers in the central region of the Silicon-Tungsten calorimeter of the proposed International Large Detector and achieves an accurate simulation of differential distributions including for the first time the shape of the minimum-ionizing-particle peak.
Automating the ABCD method with machine learning
Automating the ABCD method with machine learning significantly improves performance in terms of ABCD closure, background rejection and signal contamination, and uncovers a previously unappreciated aspect of the method: its accuracy hinges on having low signal contamination in control regions not just overall, but relative to the signal fraction in the signal region.
Mixture-of-theories Training: Can We Find New Physics and Anomalies Better by Mixing Physical Theories?
: Model–independent search strategies have been increasingly proposed in recent years because on the one hand there has been no clear signal for new physics and on the other hand there is a lack of a
A Normalized Autoencoder for LHC Triggers
The normalized autoencoder combines a standard bottleneck architecture with a well-defined probabilistic description and works better than all available autoencoders for top vs QCD jets and reliably identifies different dark-jet signals.
Quantum Anomaly Detection for Collider Physics
An anomaly detection task in the four-lepton final state at the Large Hadron Collider that is limited by a small dataset is studied and there is no evidence that QML provides any advantage over classical ML.
Boosting mono-jet searches with model-agnostic machine learning
It is shown how weakly supervised machine learning can improve the sensitivity of LHC mono-jet searches to new physics models with anomalous jet dynamics and the discovery potential of an existing generic search can be boosted considerably.
Simulation-based Anomaly Detection for Multileptons at the LHC
Decays of Higgs boson-like particles into multileptons is a well-motivated process for investigating physics beyond the Standard Model (SM). A unique feature of this final state is the precision with
Deep learning applications for quality control in particle detector construction
This study focuses on the construction steps of a silicon detector, which involve forming a mechanical structure with the sensor and wire bonding individual cells to electronics for reading out signals.


Variational autoencoders for new physics mining at the Large Hadron Collider
A one-sided threshold test to isolate previously unseen processes as outlier events is developed, which could inspire new-physics model building and new experimental searches, and be complementary to classic LHC searches.
Adversarially-trained autoencoders for robust unsupervised new physics searches
It is proposed to combine the autoencoder with an adversarial neural network to remove its sensitivity to the smearing of the final-state objects and it is shown that one can achieve a robust anomaly detection in resonance-induced resonance.
Novelty Detection Meets Collider Physics
The potential role of novelty detection in collider physics is demonstrated, using autoencoder-based deep neural network and a set of density-based novelty evaluators, which are sensitive to the clustering of unknown-pattern testing data or new-physics signal events for the design of detection algorithms.
Adversarially Learned Anomaly Detection
This work proposes an anomaly detection method, Adversarially Learned Anomaly Detection (ALAD), that derives adversarially learned features for the anomaly detection task that achieves state-of-the-art performance on a range of image and tabular datasets while being several hundred-fold faster at test time than the only published GAN-based method.
An Encoding Adversarial Network for Anomaly Detection
This work develops an alternative approach for anomaly detection, based on an Encoding Adversarial Network (AnoEAN), which maps the data in a latent space (decision space), where the detection of anomalies is done directly by calculating a score.
Anomaly Detection for Resonant New Physics with Machine Learning.
A new model-agnostic anomaly detection technique that naturally benefits from modern machine learning algorithms is presented that can turn a modest 2σ excess into a 7σ excess for a model with an intermediate BSM particle that is not currently targeted by a dedicated search.
Searching for new physics with deep autoencoders
A potentially powerful new method of searching for new physics at the LHC, using autoencoders and unsupervised deep learning, which opens up the exciting possibility of training directly on actual data to discover new physics with no prior expectations or theory prejudice.
QCD or what?
This work shows how adversarial autoencoder networks, trained only on QCD jets, identify jets from decays of arbitrary heavy resonances using 4-vectors, allowing for a general and at the same time easily controllable search for new physics.
Learning multivariate new physics
We discuss a method that employs a multilayer perceptron to detect deviations from a reference model in large multivariate datasets. Our data analysis strategy does not rely on any prior assumption
Extending the search for new resonances with machine learning
This work presents a new extension of the bump hunt that naturally benefits from modern machine learning algorithms while remaining model agnostic, based on the classification without labels (CWoLa) method where the invariant mass is used to create two potentially mixed samples.