mlsanityData to 14 Oct 2026

Bump Hunting in Latent Space

arXiv 2103.06595 ↗First posted 11 Mar 2021hep-ph cs.LG hep-excited by 19

Not on the map. Why?

Abstract (arXiv)

Unsupervised anomaly detection could be crucial in future analyses searching for rare phenomena in large datasets, as for example collected at the LHC. To this end, we introduce a physics inspired variational autoencoder (VAE) architecture which performs competitively and robustly on the LHC Olympics Machine Learning Challenge datasets. We demonstrate how embedding some physical observables directly into the VAE latent space, while at the same time keeping the classifier manifestly agnostic to them, can help to identify and characterise features in measured spectra as caused by the presence of anomalies in a dataset.

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). Builds on 12 of its 42 references that are in the map. First posted on arXiv 11 Mar 2021.

Builds on

12 of 42 references.

References · 12

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2013Auto-Encoding Variational Bayescited by 4,053
  3. 2019On Empirical Comparisons of Optimizers for Deep Learningcited by 103
  4. 2020Anomaly Detection with Density Estimationcited by 72
  5. 2016Learning to Pivot with Adversarial Networkscited by 55
  6. 2017Classification without labels: Learning from mixed samples in high energy physicscited by 43
  7. 2020Variational Autoencoders for Anomalous Jet Taggingcited by 33
  8. 2020Simulation Assisted Likelihood-free Anomaly Detectioncited by 27
  9. 2020Adversarially Learned Anomaly Detection on CMS Open Data: re-discovering the top quarkcited by 18
  10. 2020Simulation-Assisted Decorrelation for Resonant Anomaly Detectioncited by 13
  11. 2017Decorrelated Jet Substructure Tagging using Adversarial Neural Networkscited by 12
  12. 2018On the Topic of Jets: Disentangling Quarks and Gluons at Colliderscited by 6

Built on by

Cited by year

Citing papers per year: 2021: 7; 2022: 3; 2023: 5; 2024: 1; 2025: 3.

19 papers.

Sort:

By area:

  1. 2021Autoencoders for unsupervised anomaly detection in high energy physicscited by 32
  2. 2021Better Latent Spaces for Better Autoencoderscited by 21
  3. 2022Learning new physics efficiently with nonparametric methodscited by 21
  4. 2023Quantum anomaly detection in the latent space of proton collision events at the LHCcited by 21
  5. 2023Deep Generative Models for Detector Signature Simulation: A Taxonomic Reviewcited by 18
  6. 2021Challenges for Unsupervised Anomaly Detection in Particle Physicscited by 16
  7. 2021Online-compatible Unsupervised Non-resonant Anomaly Detectioncited by 15
  8. 2022Lorentz group equivariant autoencoderscited by 15
  9. 2021Comparing Weak- and Unsupervised Methods for Resonant Anomaly Detectioncited by 13
  10. 2023Anomalies, Representations, and Self-Supervisioncited by 11
  11. 2021Latent Space Refinement for Deep Generative Modelscited by 10
  12. 2021Particle Graph Autoencoders and Differentiable, Learned Energy Mover's Distancecited by 10
7 more
  1. 2023Improving new physics searches with diffusion models for event observables and jet constituentscited by 10
  2. 2022A Detailed Study of Interpretability of Deep Neural Network based Top Taggerscited by 7
  3. 2025Tensor Network for Anomaly Detection in the Latent Space of Proton Collision Events at the LHCcited by 5
  4. 2023Triggering Dark Showers with Conditional Dual Auto-Encoderscited by 1
  5. 2025Detecting Localized Density Anomalies in Multivariate Data via Coin-Flip Statisticscited by 1
  6. 2024Toward Model-Agnostic Detection of New Physics Using Data-Driven Signal Regionscited by 0
  7. 2025TRANSIT your events into a new mass: Fast background interpolation for weakly-supervised anomaly searchescited by 0